0% found this document useful (0 votes)
58 views54 pages

10 Chapter 4

This chapter discusses a new approach for multi-objective contrast enhancement of videos based on the water cycle algorithm. It begins with an introduction to the need for effective video pre-processing techniques to improve quality. Common pre-processing techniques for videos like noise filtering, illumination correction, and contrast enhancement are described. A literature review covers conventional and soft computing based contrast enhancement methods. Then, a new contrast enhancement approach inspired by the water cycle is proposed and test results on various videos are presented.

Uploaded by

Atersaw Tigyhun
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
58 views54 pages

10 Chapter 4

This chapter discusses a new approach for multi-objective contrast enhancement of videos based on the water cycle algorithm. It begins with an introduction to the need for effective video pre-processing techniques to improve quality. Common pre-processing techniques for videos like noise filtering, illumination correction, and contrast enhancement are described. A literature review covers conventional and soft computing based contrast enhancement methods. Then, a new contrast enhancement approach inspired by the water cycle is proposed and test results on various videos are presented.

Uploaded by

Atersaw Tigyhun
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 54

MULTI OBJECTIVE CONTRAST

ENHANCEMENT BASED ON WATER


CYCLE ALGORITHM
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS
CHAPTER 4 MULTI-OBJECTIVE CONTRAST
ENHANCEMENT BASED ON WATER
CYCLE ALGORITHM

4.1 INTRODUCTION
Real time or captured images/videos are taken from publicly available databases and
are used for various purposes such as image classification, object detection and
tracking. These raw images are not suitable for analysis because of presence of
various types of noise, bad state of capturing devices, low illumination etc. This often
leads to numerous problems such as inability to segment images accurately, visual
illusions, poor detection of object boundaries, misclassification of images, distortion
of visual quality etc. Therefore effective and efficient pre-processing is required for
improving visual quality and enhancing contrast so that targets could be detected
accurately in videos.

The main aim of pre-processing techniques is to rectify the degradation of


image/video data such as de-blurring of object edges, highlight specific features, noise
removal in order to improve interpretability and perception of image information for
human viewers. In case of videos, the preprocessing technique refers to process that
manipulates raw input video sequence into a form that can be used in subsequent
steps. The literature survey reported over decade shows availability of numerous
techniques for pre-processing of videos and images. Though there are numerous
techniques available in literature but, there is no universal technique that can be used
to remove all above stated deficiencies for example, histogram based contrast
enhancement techniques are able to enhance the contrast of the images but fail to
restore the naturalness of images. The resultant image tends to have artifacts and loose
colorfulness. Soft computing based techniques are proposed to overcome these
limitation but some of them are complex in terms of implementation and
computational cost. This chapter presents a simple yet effective technique for
enhancing contrast of videos with preservation of naturalness. The technique is
inspired by soft computing principles and is widely tested on different types of videos.

The organization of chapter is as follows: next section discusses about available pre-
processing techniques for videos with major focus towards contrast stretching; section

101
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

4.3 focuses on related work on contrast enhancement is discussed under two sub-
headings of conventional and soft computing based enhancement techniques. Section
4.4 proposes new contrast enhancement approach based on water cycle algorithm.
Section 4.5 projects performance results of the proposed technique on various videos
and images. The chapter ends with conclusions and summary.

4.2 PREPROCESSING TECHNIQUES FOR VIDEOS


Pre-processing means any operation performed for analysis and manipulation of video
to perform some task. A number of video pre-processing techniques are available but
following are the most commonly applied techniques:
1. Noise Filtering
2. Illumination correction
3. Image sharpening
4. Contrast enhancement

4.2.1 Noise Filtering


Digital videos/images are used in various areas such as military, industry, medicine,
and surveillance and noise can arise in images/videos during transmission or
capturing process. The importance of digital videos/images in various applications
makes enhancement and filtering of noise a crucial and challenging task. The
presence of noise hampers generation of true information of the video, automatic
processing and can hinder visual effects. The video streams or images degraded by
noise are not able to facilitate various image processing steps. Therefore it is very
important and crucial to restore the degradation in the image data before performing
various image processing operations. Noise filtering is usually applied to enhance
appearance of image when final output is used for image segmentation, data
compression, object detection and tracking, edge detection etc. Noise filtering is a
pre-processing step in which appropriate filter is applied according to the type of
noise to remove undesired effect. The basic mechanism of filtering is applied by
convoluting the pixels in images to designed masks. There exists large number of
techniques in literature for noise filtering in images/ videos. Bilateral filter [185],
[186],[187], is one of the popular non-linear filter that uses local information to detect
detailed part of images. It is evaluated as weighted average of each pixel‘s
surrounding. The weight is based on the spatial distance and the intensity difference.

102
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

The relationship between two pixels is measured in bilateral filtering in terms of both
closeness in the domain and similarity in the range. The output of bilateral filter at
each pixel is in form of weighted average of its neighbors. The bilateral filter makes
use of both geometric closeness and photometric similarity which make it efficient in
reducing noise. Guided image filter [188], [189], [190], is an edge-preserving
smoothing filter which involves smoothing of input image by using the content of
another image called the guidance image to influence filtering process. The guidance
image can be referred as image itself, a different version of the image, or a completely
different image. The filtering operation using guidance images is much like other
filtering operation in which the statistics of a region in the guidance image are
considered while evaluating the value of output pixel. Median Filters [191] are
commonly used in various computer vision and image processing applications in
which filtering is achieved by substituting each pixel value with the median value of
the surrounding N-by-N neighborhood. Fuzzy directional filter [192] was employed to
reduce the additive impulsive noise in color videos. Fuzzy logic filters were designed
by establishing membership function and fuzzy rule base to detect noise in the
neighborhood frames. In [192], 3D fuzzy directional filter was proposed which
employed 2D fuzzy filter in t-initial frame of video. The filtering resulted from the
first stage was used in processing of the current frame of the video. At last, the current
frame was filtered using 2D filter again w.r.t. fuzzy rules based on direction
information to reduce the effect of noise. Recursive temporal LMMSE de-noising
filter[193] was put-forward to reduce noising effect in videos. It was integrated into
encoding and decoding process of video codec. The filter included spatiotemporal
adjacent homogeneous pixels which were matched with the current pixels to reduce
noise effectively. Spatio-temporal filters have been attempted in [194] for reducing
Gaussian noise in dynamic videos where temporal gaussian smoothing was combined
with fast digital path approach. The study on noise filtering reveals that overall
performance of the system significantly decreases with increase in noise. Therefore
researchers need to develop and work on image reconstruction by removing noise and
blurriness, in images to make them human perceptible.

4.2.2 Illumination Correction

Various applications like object detection and tracking, foreground extraction, video
surveillance, deal with videos or images that suffer from degradation in quality due to

103
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

drastic change in illumination conditions. This is a major issue targeted by


illumination corrections techniques. The variation in illumination occurs due to
reasons of our everyday life such as light switch on or off, movement of clouds in
front of sun, variation of sunlight during day, shadows, opening or closing of a
curtain, etc. The illumination variation will result in intensity changes of particular
pixel or entire pixels of images over time or change in contrast from one frame to
other frame in case of videos. Sudden illumination variation leads to problems such as
sudden information loss, unreliable object detection, misunderstanding between
foreground and background regions and drastic increase in falsely detection of change
regions. To deal with these problems, efficient methodology is required for
compensating illumination correction.

Histogram equalization is the most conventional image enhancement algorithm but it


cannot be used for illumination correction in images as histogram equalization
approach exploits only global information and don‘t consider local information within
neighborhood of each pixel of illumination variation. To overcome this limitation
many researchers have proposed numerous techniques to work under illumination
variation and some of the referenced work that can be used to provide visual pleasing
or informative image include automatic illumination correction using feed-forward
neural network [195], illumination correction using genetic algorithm [196],
illumination correction based on Gaussian mixture model [197], average intensity
approach for illumination adjustment [198], illumination estimation for outdoor
scenes [199].

The authors in [195] presented automatic illumination correction method based on


neural network for color and gray scale imaging scenario. They applied neural
network for color correction in which learning was performed with the help of one or
more pairs of color palettes between two illumination conditions and was then applied
to every pixel of the successive frame of the image. Illumination based contrast
enhancement approach using genetic algorithm was proposed in [196] for night-time
videos. The algorithm consists of four steps. The first step deals with conversion of
input video from RGB to HSI domain. The second step deals with extraction of
illumination component obtained by decomposing input frame into intensity and
color. In the next step, illumination enhancement was done using genetic algorithm
and finally image reconstruction was done by converting HSI representation back into

104
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

RGB representation. Mixture Gaussian based illumination correction method was


introduced in [197] in which global intensity factor was evaluated for correction of
image intensity under the assumption of Gaussian distribution of stationary pixels.
The researchers in [198] proposed two methods to deal with the problem of
illumination correction in images and videos. They used average intensity for
evaluating video illumination difference to output threshold for fixing the image
intensity and secondly, applied dynamic area histogram equalization for solving
problem of luminance difference. An image based framework for estimating
illumination was proposed in for outdoor scenes [199]. The light estimation process
for a fixed camera was described using a linear model of outdoor images. During
initialization stage, early morning images were captured and areas were selected using
upward normal using a few brushes.. The above stated solutions are devoted to
artifacts suppression that can occur due to variation in illumination and will help in
enhancing the visual quality of the images. Other studies are discussed in section 4.3.

4.2.3 Image Sharpening

Digital images have become core information carrier due to their explosive
development in the field of internet and rapid increase in growth of image acquisition
devices. People like to get a large amount of detailed information from images and
therefore it is very important to maintain visual quality. Images or videos are
degraded by contrast effect due to errors and problems in image acquisition devices.
Image sharpening is a very popular type of enhancement is used in numerous practical
applications with aim of utilizing and improving visual quality of images from human
visual point of view. Image contrast will be improved by image sharpening technique
by putting together scaled edge information around object boundaries in an image.
The contrast of images will be enhanced to represent fine details of the image with
reduced blurring effect after sharpening operation. This technique has become a well
known issue for various practical applications such as object detection and tracking in
videos, image segmentation, and automatic guidance in military system and medical
imaging. The sharpened image will have sharp boundaries with improved intensity
values aiding in correct classification of pixels. Work in this direction has already
flourished a lot and many well known algorithms on image sharpening methods are
readily available today. Some of image sharpening techniques[200-203] have been
referred for interested readers.

105
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

4.2.4 Contrast Enhancement

Contrast Enhancement is one of the important steps of image/ video processing that
has contributed to various fields such as computer vision, pattern recognition and
digital images processing. Contrast enhancement is process employed on images or
videos to raise dynamic gray level range. It can also act as a pre-processing step in
various video applications by redistributing intensity range of image or by modifying
histogram of an image so that they can be interpreted efficiently by humans or
machines. A number of applications like object detection and tracking, anomaly
detection are governed by amount of information that could be captured by cameras.
Although some success has been attained with invent of sophisticated cameras but
constraints imposed by weather like low illumination, fog and haze have not been still
completely overpowered. An image or video captured in bad weather is bound to have
low contrast that can attenuate performance of various computer vision tasks. Most of
image enhancement methods tend to improve contrast and highlight details by
processing individual pixel level values either locally or globally. Local enhancement
methods work on parts of image or frame whereas global methods operate on whole
image. Global contrast stretching methods have been successful in restoring contrasts
but problems like overcompensation, truncation of pixel values amounting to loss of
information tends to creep in. An efficient contrast enhancement technique should
have properties of noise tolerance, uniform enhancement, brightness preservation and
utilization of resources. It is crucial to study various properties of contrast
enhancement techniques for further utilization in numerous applications. Therefore,
various considerations such as varied illumination conditions, camera perspective,
noise, have to be made during selection of numerous contrast enhancement
characteristics different applications. The next section is devoted to discussion on
various contrast enhancement studies.

4.3 CONTRAST ENHANCEMENT BASED STUDIES


Numerous enhancement methods have been proposed in the literature to overcome the
difficulties of contrast enhancement in videos/images. These have been classified into
two major categories in this chapter: Conventional contrast enhancement methods and
Soft computing based methods. Conventional contrast enhancement methods include
histogram equalization; gamma correction, contrast stretching approaches etc are

106
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

discussed in section 4.3.1. Soft computing techniques include fuzzy logic based
methods, neural network based method and evolutionary based method have also been
applied for preserving brightness and enhancing contrast of the image. Enhancement
techniques based on soft computing methods are discussed in section 4.3.2.

4.3.1 Conventional Contrast Enhancement Methods

The conventional contrast enhancement techniques are classical techniques used for
maintaining contrast of the image. In methods like Histogram Equalization (HE),
enhancement is obtained by redistribution of pixel intensities over a dynamic range.
Histogram Equalization flattens and stretches dynamic range of an image histogram
and gives an over-all contrast improvement. Histogram Equalization has been used in
all fields like Medical, Radar, Satellite and Microstructure image processing etc and is
available in most image processing packages such as Adobe Photoshop, National
Institutes of Health Image and Lispix.

Histogram Equalization methods can be categorized into two as global and local.
Global HE methods improve quality of image by normalizing distribution of
intensities over dynamic range, using histogram of entire image. It is achieved by
manipulating intensity distribution using its cumulative distribution function (CDF) so
that resultant image may have a linear distribution of intensities. Local Histogram
Equalization (LHE) methods use histogram intensity statistics of the neighborhood
pixels of an image for equalization. These techniques usually divide the original
image into several non-overlapped sub-blocks and perform histogram equalization on
the individual sub-blocks. The resultant image is produced by merging sub-blocks
using bilinear interpolation method. The major drawback of these methods is
introduction of checkerboard effect which appears near boundaries of sub-blocks. The
enhanced image using Histogram Equalization tends to have unnatural enhancement
and intensity saturation artifacts due to the error in brightness because of mean-
shifting and tends to introduce washed-out effect in the output image. Conventional
HE is one of the mostly used contrast enhancement techniques but is not suitable in
applications where brightness preservation property is required. In the recent years,
many researchers have proposed several useful algorithms to overcome problems of
Histogram Equalization. To overcome brightness preservation problem, various
histogram equalization methods such as Mean preserving Bi-Histogram Equalization
(BBHE), equal area Dualistic Sub-Image Histogram Equalization (DSIHE), Minimum

107
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

Mean Brightness Error Bi-Histogram Equalization (MMBEBHE), Recursive Mean-


Spread Histogram Equalization (RMSHE) were developed.

Kim et al. [204] proposed brightness preservation method known as Brightness


Preserving Bi-Histogram Equalization (BBHE) which performs segmentation of input
image into two parts on the basis of mean and performed equalization of both
components individually. Another variant of BBHE that segments image on the basis
of median was proposed by Wan et al.[205] known as equal area Dualistic Sub-Image
Histogram Equalization(DSIHE). Another extension of BBHE known as Minimum
Mean Brightness Error Bi-Histogram Equalization (MMBEBHE) was proposed by
Chen and Ramli[206]. These methods were found to be suitable to images having
uniform intensity distribution. Recursive Mean Separate Histogram Equalization
(RMSHE) was proposed in which the histogram of the given image is partitioned
recursively. Each segment was equalized independently and the union of all the
segments gives the contrast-enhanced output. Computational cost was clearly a
disadvantage of this method. Some authors have also tried to extend the principles of
HE to color images while working in RGB color space or in non linear color space
like YCrCb or HSI. One of the most famous approaches of the first class is 3-D
histogram equalization [207] proposed by Trahanias and Venetsanopoulos. They
proposed a 3-D cumulative distribution function (CDF) for bringing into account
correlation between R, G and B components. Another method that uses multiple 2-D
histograms rather than single 3-D histogram has been given by Menotti et al. [208].
The method looks for correlation of color channels among two different histograms
and performs equalization thereafter. Han et al. in [209] has tried to reduce over
enhancement of 3-D histogram technique and low contrast of 2-D histogram but has
ignored correlation between R, G and B channels.

Another common method for enhancing the contrast of images is Gamma correction.
Gamma correction with weighted distribution method was introduced by Huang et al.
[210] for efficient contrast enhancement in images. This work is an automatic
transformation approach to increase brightness of dimmed images using probability
distribution method of luminance pixels. The complexity of method was reduced by
using temporal information with respect to difference between each frame. It was also
demonstrated that proposed approach was capable of implementation in real time
environment according to time consumption analysis of work. Recently, a similar

108
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

investigation was carried out by Gupta et.al [211] in which they had applied Gamma
correction with weighted probability distribution method for contrast enhancement in
images. The proposed approach used weighting distribution function for modifying
statistical histogram and reduced generation of various adverse effects. The method
was tested on images having variation in illumination due to back light effect, light
source location, cloud cover, sunshine intensity, etc. and was shown to achieve high
Peak signal noise ratio.

Two factors namely lighting condition and structural distortion were considered by
Janga et.al [212] to improve visual quality for contrast enhancement in images. Their
work consisted of two major steps. The first step deals with estimation of lighting
condition computed using dynamic range along edges of the image. The second step
deals with contrast enhancement process adjusted by taking into consideration both
estimated lighting condition and various order of luminance levels. Compared to
state-of-art methods, the proposed approach was able to achieve better visual quality
of different images by raising various parameters such as entropy, tone-mapped image
quality index, average structural fidelity and enhancement performance measure. A
low contrast enhancement technique based on singular value decomposition was
proposed by Atta et al. [213]. In this method, a single value matrix of the equalized
image was computed using weighted sum of singular matrices of input image and its
global histogram equalization (GHE) image. It was shown that proposed approach
does not produce satisfactory results for some low contrast images. The method was
qualitatively and quantitatively evaluated against various conventional algorithms
such as global histogram equalization and local histogram equalization approaches.
Overall Brightness and Local Contrast Adaptive Enhancement algorithm was applied
by Zhou et al. [214] based on HSI color-space model. The work consisted of three
steps. The first stage of the three step method was global brightness adaptive
adjustment and the second stage deals with adaptive local contrast enhancement. The
last stage deals with color restoration process. The method yielded successful results
for color images with low illumination.

4.3.2 Soft Computing based Image Enhancement Methods

Soft computing based approaches have been used to improve contrast of


videos/frames. The major reason for utilization of soft computing approaches for
contrast enhancement is difficulties associates with traditional methods like brightness

109
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

preservation, over enhancement etc. This led to use of soft computing based
techniques in the field of image/ video contrast enhancement. Several soft computing
techniques have been used for contrast enhancement in images/videos and this section
discusses some of these techniques.

Histogram Equalization has also been implemented using artificial neural network
based studies and Thomas H. Hildebrandt [215] was the first to propose and
implement a circuit for generalized histogram equalization. Few weight based
equalization methods like weighted threshold HE (WTHE) [216] had been proposed
to add adaptivity and ease of control to the enhancement process. These methods tend
to modify probability density function by suitable weights before performing
equalization and perform normalization afterwards with addition of some adjustment
factor. Weight Clustering HE (WCHE) [217] was also developed in 2008 which had
its basis on adaptive change of weights. Another Local HE based technique was
proposed by Chitwong et al. [218] that utilized efficacies of Hopfield networks. The
method uses fuzzy c-means clustering and competitive hopfield neural network for
segmentation of image while performing equalization of both components
individually. In [219], authors have presented genetic algorithm based method using
wavelet neural network for image contrast enhancement. They had applied in
complete beta transform to provide non-linear gray transform curve for global image
contrast enhancement. The method employed genetic algorithms to determine optimal
gray transform parameters and wavelet neural networks were applied for
approximation in complete beta transform. They had applied discrete stationary
wavelet transform to enhance local contrast of image. The final output resulted from
union of local enhanced image and global enhance image. The obtained results
showed that proposed approach was able to enhance contrast of image greatly and it
was also found that the method reduced noise and background blur better than state-
of-the art methods.

Fuzzy logic has also been used for various areas of digital image processing in recent
years. Fuzzy image processing approach comprises of three steps: image fuzzification,
manipulation of membership values and image defuzzificiation. The image contrast
enhancement using fuzzy logic is based on fuzzy modeling of images. Many
techniques based on fuzzy logic have been proposed for image contrast enhancement.
Debdoot et al. [220] proposed modified version of HE based on fuzzy statistics of

110
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

digital images known as Brightness Preserving Dynamic Fuzzy Histogram


Equalization (BPDFHE) to handle inexactness of gray level values. Another fuzzy
logic based technique (fuzzy histogram equalization-FHE) was proposed by
Magudeeswaran and Ravichandaran [221] for improvement of contrast. The approach
generates fuzzy histograms for original image using fuzzy set theory and follows it
with segmentation of image based on median. The sub-images were then
independently equalized to preserve brightness. Fuzzy logic has been exploited by
Hammadulu et al. in [222][223] for proposing solutions for contrast enhancement of
color images. In [222], Gaussian membership function was used to fuzzify colour
intensity of the image. The general intensification operation of sigmoid type was
applied to carry out enhancement of fuzzified image which was dependent on two
parameters: crossover point and intensification parameter. Further, the optimal values
of these operators were chosen using constrained fuzzy optimization. Various visual
and quality factors were considered to optimize entropy. The effectiveness of
proposed method was evaluated against histogram equalization approach and results
proved that fuzzy based approach outperforms histogram equalization approach. In
[223], author had categorized images into two categories: exposed and overexposed
image regions where amount of exposure was indicated with help of a parameter. The
underexposed region of image was exposed using Gaussian membership function
which was used for fuzzification. On the other hand overexposed regions of the image
were fuzzified using triangular membership function. This approach used generalized
intensification operator of sigmoid type for enhancement of fuzzified image. The
enhancement was also carried out using a power-law transformation operation that
was dependent on gamma parameter. Constraint fuzzy optimization was used to select
optimal values of these parameters. The appearance of images was evaluated using
entropy and visual factors.

Nature inspired techniques have been successfully exploited using methods such as
genetic algorithm, particle swarm optimization, ant colony optimization, simulated
annealing for contrast enhancement. P. Shanmugavadivu in [224], [225] had used
concept of histogram segmentation and multi objective functions for enhancement of
images. In [224], the author optimized Bi-Histogram Equalization approach for
improving contrast of input image. The technique segmented input image histogram
into two sub histogram based on its mean and weighting constraints were applied to

111
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

each sub-histogram. The resultant histograms were equalized independently and


brightness and contrast-enhanced output image was produced by their union. Particle
Swarm Optimization was applied during weighting constraints formulation to search
optimal constraints to maximize degree of enhancement. The approach was shown to
be simple and computationally inexpensive. Another work was detailed by
Shanmugavadivu et.al [225] using multi objective histogram equalization and particle
swarm optimization approach to enhance contrast of images. In this method,
histogram of input image was segmented into two by applying Otsu‘s threshold. The
formulated set of optimized weighing constraints was applied on every sub-image.
Further, each sub-image was equalization individually and the result of their union
produced brightness preserved output image. The optimal constraints were found
using particle swarm optimization technique. The effectiveness and usefulness of this
approach was shown against contemporary methods in terms of entropy and contrast
improvement index. Another important work in this direction for enhancing image
was introduced by Masra et al. [226] using histogram equalization and particles
swarm optimization. In this, the input image was partitioned into three different
channels i.e. red, green and blue and applied particle swarm optimization was applied
to each channel for computing its optimal fitness value. Then, computed fitness value
was used for Histogram equalization normalization and at last, the processed colour
image was merged back to RGB Image. Application of particle swarm optimization to
image enhancement was shown to be effective than conventional histogram
equalization approach. An algorithm based on local histogram approach using particle
swarm optimization method for contrast enhancement in images was proposed by
Wang et al. [227]. The aim was to design an algorithm applicable to low clarity
images due to variation in illumination conditions. In this work, sectorized basis
equalization was performed and enhancement of each sector was done by matching to
a uniformly-distributed target histogram. Gaussian mask was applied with weighted
sum to decrease sudden changes at the sector boundaries. Particle Swarm optimization
was used to select sector center and determine mitigation of boundary discontinuities.

Genetic algorithms have been applied for brightness preserving and enhancing
contrast of gray scale and coloured images. Munteanu et al. [228] proposed
application of transformation function to each pixel of input image. Genetic
Algorithm was used to extract parameters of transformation function. The

112
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

performance of GA based histogram equalization approach for contrast enhancement


was compared against various automatic enhancement techniques such as contrast
stretching, histogram equalization method. Both subjective and objective evaluation
proved the efficiency of proposed approach. F. Saitosh [229] used Genetic Algorithm
to represent relation between input and output gray levels using a lookup table in
which chromosomes were evaluated using edge intensities. Another technique for
local contrast enhancement using genetic algorithm was introduced by Guruvareddy
et al. [230] for gray scale images and RGB colour images. The proposed approach
was divided into two steps. The first step was a pre-enhancement step also known as
local statistic based image enhancement and second step was used to enhance local
contrast by applying genetic algorithm based approach. Genetic algorithm was used to
find optimal contrast parameter for contrast enhancement. The proposed approach
was evaluated on colour images as well as gray scale images and compared against
state-of-art contrast enhancement techniques. Excessive contrast enhancement in
images is a pertinent problem in the domain of global image enhancement histogram
equalization based techniques. Real coded genetic algorithm was developed by Babu
et al. [231] to overcome this limitation. In the proposed approach, the input image
histogram was partitioned into two sub histograms using threshold value obtained by
applying Otsu's optimality principle. The optimal contrast enhancement parameters
were used to modify sub histograms and real coded genetic algorithm was used to
select an optimal value of these parameters. The contrast enhanced image was
produced using union of the updated sub histograms. The method portrays promising
results for low contrast MRI brain images. The method exhibits better performance in
terms of quantitative metrics such as natural image quality evaluator and discrete
entropy. In [232], histogram based image enhancement technique using genetic
algorithm was introduced by Sedighi et.al. In this work, histogram of original image
was divided into one or more separating point and traditional histogram equalization
approach was applied to each sub-image. An optimal point was selected using genetic
algorithm for separating histogram. Image quality measurement was used to design
fitness function for preserving the information of original image. Experimental results
proves that Genetic algorithm based histogram equalization approach was better than
conventional histogram equalization image enhancement techniques. Artificial bee
colony optimization technique was used by Dra et al. [233] for image contrast
enhancement. The artificial bee colony optimization technique worked in four stages.

113
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

The first stage deals with the initialization of solution. The second stage known as
employed bee stage creates new solution from randomly chosen solutions. The third
stage i.e. onlooker stage looked for best solution and final stage i.e. scout stage
replaced inactive solution with a new generated randomly. This method was
compared with meta-heuristic algorithm such as genetic algorithm and various
conventional algorithms such as grey- level grouping, adaptive grey-level grouping
and histogram equalization for performance evaluation. Furthermore, the proposed
approach can also be implemented on color images. Hoseini et al. [234] applied
hybridization of ant colony optimization, genetic algorithms and simulated annealing
for improving contrast of images. Enhancement was achieved by applying global
intensity transformation grey scale images. The transfer function generated using ant
colony optimization was used to map the input intensities to output intensities. The
transfer function was tuned by applying local search technique known as simulated
annealing. Furthermore, Genetic algorithm was applied to control the parameters of
ant colony optimization for preserving naturalness of images. The performance of the
proposed approach was evaluated subjectively and objectively against algorithms
such as histogram equalization, fuzzy approach, linear contrast stretching etc.
Evolution based studies like genetic algorithm (GA) and particle swarm optimization
(PSO) have also been hybridized by various researchers to propose challenging
solutions for contrast enhancement of images. In order to enhance contrast of grey
scale images, problem of image enhancement has been framed as an optimization
problem by Apurva & Ashish [235] and PSO has been utilized to attain maximum
value for edge based contrast of image. The proposed method was compared with
various contrast enhancement techniques such as GA based image enhancement,
histogram equalization, and was shown to achieve better results.

The studies discussed above justify use of various soft computing based approaches
developed for contrast enhancement in images. Among these, evolutionary algorithms
are one of the mostly used techniques as it is difficult to develop a rule based or
training based system for this task. This may be attributed to the nature of problem
being targeted and associated complexities involved in the process. Driven by above
finding, this chapter proposes a modified histogram equalization approach to enhance
contrast of image by preserving colorfulness and brightness in complex images. The
method has also been extensively tested for performance evaluations.

114
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

4.4 WATER CYCLE ALGORITHM BASED MULTI-


OBJECTIVE CONTRAST ENHANCEMENT APPROACH

A number of applications like object detection and tracking, anomaly detection are
governed by amount of information that could be captured by cameras. Such hazards
are not still completely overpowered and make the task of enhancing and sharpening
images or videos a challenging and an evergreen problem. Most of image
enhancement methods tend to improve contrast and highlight details by processing
individual pixel level values either locally or globally. Global contrast stretching
methods like histogram equalization(HE) have been successful in restoring contrast
but problems like overcompensation, truncation of pixel values amounting to loss of
information and other types of losses tends to creep in. Artifacts may be introduced
and images may lose its colorfulness. In order to overcome these situations, a novel
histogram equalization method inspired by principles of Water Cycle Optimization
Algorithm (WCA) has been proposed. The proposed method formulates the problem
of enhancement of contrast as optimization problem and solves it with help of water
cycle optimization method. The proposed method converts input frame to YCrCb
domain and extracts its Y channel. The Y channel of input frame is smoothened using
Gaussian low pass filter to suppress useless information. The frame is then portioned
into background and foreground sub-frames using Ostu‘s 2D thresholding principle.
The foreground and background are then subjected to suitably designed constraints
and intensity is manipulated using an improved version of histogram equalization by
preserving naturalness of frame using WCA. WCA helps to select an optimal value of
parameters based on combination of three objective functions suitably framed such
that over enhancement can be negated and colorfulness of frame could be preserved.
Color component is restored by adding CrCb channel to equalized image to mitigate
loss of colorfulness. Proposed approach works on YCbCr space and a novel multi-
objective function for evaluation of image quality is designed for preservation of color
and naturalness. Multi objective function has been utilized in water cycle optimization
algorithm to extract optimal values of parameters to suitably control enhancement.

4.4.1 Outline
Consider an input image I of size M*N with intensity in the range of [ , ],
the probability density function ( ) for any level rk is given as:

115
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

( )
( ) (4.1)
( )

where ( ) represents frequency of occurrence of level rk in image, M*N defines the


total number of pixels in image and L is total number of grey levels in image.

The CDF (cumulative density function) may be given as

( ) ∑ ( ) (4.2)

Standard histogram equalization maps an image from narrow intensity range to entire
intensity range of [ , ] using CDF using Eq. 4.3.

( ) ( ) ( ) (4.3)
Histogram equalization is a traditional contrast enhancement approach that flattens
histogram and imposes a noteworthy modification in brightness of image. HE based
techniques suffer from problem of mean shift, preservation of details, over

Figure 4-1 Proposed methodology for contrast enhancement

116
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

enhancement and loss of colourfulness in case of coloured images. These problems


creep in because of global enhancement mechanism opted by HE resulting in over
enhancement. Such problems could be negated if enhancement of intensity can be
applied in a controlled manner. The problem can be tackled effectively with help of
soft computing technique and one such technique is discussed here. The main
objective of this technique is to modify basic HE mechanism to generate a visually
pleasing image and control enhancement of contrast with help of water cycle based
optimization algorithm. The complete methodology is elaborated in Figure 4-1. The
proposed technique consists of five major steps as (i) pre-processing in which
redundant information in frame is removed; (ii) segmentation of input images into
foreground and background using thresholding; (iii) modification of segmented image
using suitably defined constraints, (iv) using water cycle algorithm to extract optimal
values of constraint parameters (v) performing enhancement of input frame using
optimal values of constraints resulting in final enhanced version of image being
generated. These steps are explained in detail for better understanding of readers.

4.4.2 Pre-processing of Input Frame

In the proposed method, the input video/image sequence is transferred to YCbCr


colour model and luminance(Y) component is extracted. Y component is more prone
to dehazing or other artifacts since it is very similar to gray scale version of image.
This also helps to reduce computational complexity as information from only one
channel will be processed. The Y-channel contains rich boundary details which can
cause redundant information to flow to next phase. In order to prevent flow of
redundant information to next stages, smoothening of input frame has been done. The
smoothening has been done using a 3x3 Gaussian filter. The resultant image i.e.
smoothed Y-channel reflects uniform distribution of real scene information. This
smoothened Y-channel is passed to the next stages of proposed methodology for
further processing.

4.4.3 Segmentation of Input Image using Ostu’s 2D Thresholding

Thresholding divides an input image into foreground and background which can
further be equalized separately in order to improve contrast of individual regions.
Ostu‘s method [236] is one of the most commonly used approaches to automatically
segment image into two distinct classes. Ostu‘s algorithm searches for a threshold that

117
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

maximizes inter class variance between foreground and background regions defined
as weighted sum of variances of the two classes:

( ) ( ( ) ( )) ( ( ) ( )) (4.4)

where ( ) and ( ) means average brightness of background and foreground


thresholded by T, mean brightness of whole image is given by A(Y). and are
cumulative probabilities of background and foreground respectively defined as
∑ (4.5)

∑ (4.6)

Otsu‘s method exhibits relatively good performance for bimodal histogram


distribution but is not able to generate an optimal threshold when objects in frame are
of small size, or if variances of object and background intensities gets big, or if image
is too noisy. Due to one-dimensional Otsu algorithm's poor adaptability to noisy
image segmentation, a two dimensional Otsu algorithm [237] was introduced. Two
dimensional Ostu‘s algorithm has been widely applied for segmenting images because
of its content independent attributes. Two dimensional Ostu‘s algorithm makes use of
values of pixel neighbours together with its own value to extract an optimal threshold
for improvement of binarizaion results. This makes it suitable to segment those
images with small sized object and images with lots of noise. Two dimensional Ostu‘s
method works by forming a pair of pixel gray level(i) and average of its
neighbours(j); and each such pair belongs to a two dimensional bin with total number
of bins equal to L x L, where L is number of grey levels and neighbouring grey
values. The joint probability mass function of such two dimensional histogram may
be defined as number of occurrences f(i,j) of pair (i,j), divided by total number of
pixels in image ( )
( )
(4.7)

where ∑ ∑ ( ) and ∑ ∑ (4.8)

Let segmentation to be [S,T] and assuming that two dimensional histogram consists of
only two regions namely foreground and background, different probabilities of these
regions may be specified as

∑ ∑ (4.9)

118
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

∑ ∑ (4.10)

Mean vectors corresponding to these two regions are given as

[ ] ∑ ∑ ∑ ∑ (4.11)

[ ] ∑ ∑ ∑ ∑ (4.12)

Inter class variance of these regions can be specified as

( ) ( ) (4.13)

The optimal threshold could be found by maximizing interclass variance of two


classes given and is given by

( ( )) ( ) ( ) (4.14)

The input image is segmented into foreground (IF) and background (IB) sub-images
with help of . The threshold generated by two dimensional Ostu‘s method will
provide a better segmentation as compared to standard Ostu‘s method for images with
multimodal distribution and noise. This is because two dimensional Ostu/s method
considers neighbourhood pixels for extracting threshold value. The readers may refer
to study [237] for further details about Ostu‘s two dimensional thresholding.

4.4.4 Modification of Background and Foreground Sub-images

Probability distributions for foreword sub-image (IF) and background sub-images (IB)
obtained in previous step can be calculated using Eq. 4.1 as ( ) and ( ).
In order to suitably enhanced these sub-images; individual probability distributions
are subjected to suitably defined constraints and modified accordingly. The modified
probability density functions for foreground ( ( )) and back-
ground ( ( ) ) frames can be specified as:

( )
( )
( ) {. / ( ) (4.15)
( )

( ( )) τ

( )
( )
( ) {. / ( ) (4.16)
( )

119
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

( ( )) ( ( ))

Mean of modified probability distribution is calculated for both foreground and


background sub images and is subtracted from mean probability distribution of non-
modified sub-images. The relative difference among background and foreground
distributions is added to ( ) and ( ) respectively to maintain
average brightness. The cumulative distribution functions using ( ) and
( ) for background and foreground is calculated as ( ( )) and
( ( )) using Eq. 4.2. Histogram equalization procedure can then be
applied Eq. 4.3 and new sub-images could be generated as

( ) ( ) ( ( )) (4.17)

( ) ( ) ( ( )) ( ( )) (4.18)

It can be seen in Eq. 4.15 and Eq. 4.16, that probability distribution functions of both
foreground and background are clamped with respect to certain threshold values.
These constraints are applied to control effects of dominating intensities and ignore
the effects of intensities with small PDF values. These are controlled with help of four
parameters (q, r, s, t) used in Eq. 4.15 and Eq. 4.16. Values of controlling parameters
(r, t) are fixed in the range from 0.1-1.0 and are used to control degree of
enhancement. If value of these parameters goes above this range, then over
enhancement tends to creeps in image. The degree or amount of enhancement is
controlled by power parameters (q,s); it helps in reallocation of less probable levels in
the corresponding sub-images with more probable levels. These are also confined to
range between (0.1 – 1.0) as values within this range helps in preservation of visual
details of the image. When value of power factor approach 1.0, the procedure behaves
like standard histogram equalization, when value goes beyond 1.0, more weight is
added to high probability levels and these constraints impose an even stronger effect
than HE which may result in over enhancement. The defined constraints are applied to
both sub-images separately and both are combined to generate new image Inew which
is passed to next step for constraint optimization.

4.4.5 WCA based Optimization of Constraints Parameters


The process of modified histogram equalization can be controlled with help of four
parameters, (q,r,s,t), defined in previous sub-section. The values of these parameters

120
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

range from (0.1-1.0). It is clear from the above discussion that combination of values
of these four parameters will result in production of different background and
foreground sub-images. Out of all these combinations, one will correspond to optimal
values of these parameters for which background and foreground sub images are
modified optimally. Since number of such combinations can be very large therefore
finding an optimal combination of such parameters is a computationally complex
problem. Such problems can be solved using soft computing based variants since soft
computing techniques have profound history in finding solutions for such problems.
One such recently proposed technique is water cycle optimization algorithm and this
section discusses how water cycle algorithm has been used to extract an optimal
combination of these parameters. We first discuss basic water cycle algorithm and
then propose use of water cycle algorithm to generate optimal value of parameters.

4.4.5.1 Water cycle algorithm

Water Cycle Algorithm(WCA) is new population based meta-heuristic algorithm


based on the observation of nature‘s water cycle and finds solutions mimicking flow
of rivers and streams toward sea[238] [239]. In nature‘s water cycle, water from
rainfall gets accumulated in rivers and streams; streams flow towards rivers and rivers
flow towards sea with an aim to reach the lowest point i.e. sea. WCA tries to create
this phenomenon by creating an initial population of design variables or in other
words population of streams (raindrops) after assuming occurrence of rainfall or
precipitation. The best individual (best raindrop) i.e. one having least or max value of
cost function is chosen as a sea.

(4.19)

[ ]

[ ]

Then, a number of good raindrops i.e. solutions having cost function closest to current
best are chosen as rivers and rest of raindrops are considered as streams which flow to
the rivers and sea. For implementation of this effect, an initial population with
dimensions Npop × D is created (Eq. 4.19) where D represents number of design

121
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

(a)

(b)
Figure 4-2 Water cycle optimization process (a) Flow of streams to rivers, (b)
optimization process
variables and Npop is population size. Out of total of streams created initially,
represents best individuals from population which are designated as sea and rivers.
The rest of population are considered as streams flowing into rivers or into
sea directly. Depending on their magnitude of flow, each river absorbs water from the
streams. The amount of water in a stream entering a river and/or sea varies from other
streams. Sea is assumed to be most downhill location and rivers flow to the sea.
Figure 4.2 illustrates complete WCA optimization process and depicts flow of rivers
and streams towards sea. The figure also shows change in position of a stream after
iteration.

In order to designate/assign raindrops to the rivers and sea depending on the intensity
of the flow, the following equation is used

,| | - (4.20)

where is the number of streams which flow into the specific rivers and the sea;
is the cost of respective raindrop.

Flow of rivers to sea and streams to rivers is modelled as

( ) (4.21)

( ) (4.22)

122
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

where C is number between 1 and 2. Initial value of X may be in the range


( ) where d is current distance between stream and river. X is
randomly chosen distance to depict flow of streams to river along the connecting line
(Refer Figure 4.2).

Evaporation process is similar to exploitation and is modelled to prevent premature


convergence to local minima. Evaporation may lead to more precipitation and
algorithm checks whether river/stream is sufficiently close to sea to enable
evaporation process to occur. Following criterion is used for occurrence of
evaporation condition between a river and the sea:

‖⃗ ⃗ ‖ (4.23)

where is a small number close to zero and value of adaptively decreases


for every iteration as follows:
( )
( ) ( ) (4.24)

After evaporation, raining process is applied and new streams are formed in different
locations (similar to mutation operator in the Genetic Algorithms). In the raining
process, new raindrops form new streams (chromosomes in terms of GA) at different
locations acting similar to mutation operator in GA. To specify locations of the newly
formed streams, the following equation is used:

( ) (4.25)

where LB and UB are lower and upper bounds for given problem. Again, the best
newly formed raindrop is considered as river flowing to the sea. The rest of new
raindrops are assumed to form new streams which flow to the rivers or may directly
flow to the sea. Termination condition of WCA may be fixed as maximum number of
iterations or small tolerance value between consecutive iterations. The readers are
advised to refer to [238] [239] for more details about water cycle algorithm.

4.4.5.2 Objective function for WCA

The main aim of proposed technique is to enhance contrast of input frame while
preserving brightness of source image. Two different functions have been used for
implementing this aspect where one will try to maximize contrast and other will be
used to preserve brightness. For preservation of brightness, we propose difference in

123
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

average intensities of enhanced and original image as one of the function which can
be calculated as:

( ) ( ) (4.26)

Several methods are available to measure contrast like contrast improvement index,
edge based contrast etc. In this approach, modified contrast index used by Y. Wang et
al. [240] has been considered in which contrast of image is measured by combining
different performance measures like entropy, sum of edge based intensities and
number of edge pixels. This can be specified according to Eq. 4.27
( )
( ) ( ( ( )) ( ) (4.27)

where I is source image of M x N pixels; is visible edge image of I which can be


computed as [241]. It is calculated as the ratio between the gradient of the visible
edges between the image before and after contrast restoration. S(.) is sum of

intensities of visible image, ne represents number of edges and H represents entropy


of image.

Colourfulness index (CCI) is used to measure colourfulness of frame. CCI reflects the
richness and vivid degree of colour present in an image and is measured according to
work of Hasler et al. [242]. In order to maintain colourfulness of frame, difference of
original and enhanced frame is taken as third objective function to optimize.

( ) ( ) (4.28)

The three metrics can be combined together to get a single function as:

(4.29)

In order to make final image rich in contrast with preservation of colourfulness and
brightness it is desirable to maximize value of E and therefore Eq. 4.29 has been taken
as objective function for the problem. and are weighing factors for controlling
levels of brightness and color component enhancement of image. The ideal values for
these weights shall be small as enhancement of contrast is more priory operations
targeted by system and values of other two functions can be just maintained as actual.
The value of these weights is set experimentally depending on nature and quality of
input image. The complete optimization process implemented using water cycle
algorithm is detailed in the next section with new algorithm for contrast enhancement
also elaborated.

124
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

4.4.6 Water Cycle Enhancement Algorithm

This section illustrates how the problem of parameter detection has been solved using
water cycle algorithm and used for enhancement of input frame. The value of
proposed objective function (E) is combination of three individual functions providing
modelling of contrast, brightness and colour. According to concepts discussed in
previous sections, enhancement of a frame or image is affected by parameters
( ) and it is very difficult to choose an optimal combination for which values of
enhancement can be maximized. To make image more natural and colourful,
objective function in Eq. 4.29 was proposed. Therefore combination of ( )
values will also affect the calculation of function given in Eq. 4.29.

Based on above discussions, the problem of searching for optimal parameters is


formulated as maximization of equation for E which could be stated as follows

( ) ( ( )) (4.30)

subject to the constraints as (4.31)

is the resultant image produced by combining foreground and background


images.

The complete algorithm to perform enhancement of input image or frame is given as:

1. Input an image or frame of video and convert it to YCbCr colour space.

2. Extract Y channel and use 3x3 Gaussian mask to smoothen input image. Also
extract CbCr component of frame.

3. Use two dimensional Ostu‘s thresholding to extract appropriate threshold


value ( ) for the Y-channel of frame using Eq. 4.14.

4. Apply threshold generated in previous step to extract two sub-images from


original image as foreground (IF) and background (IB).

5. Use Water cycle algorithm for finding optimal values of (q, r, s, t) for
enhancing IF and IB

a. Initialize WCA parameters: population size (N=30), Nsr=6, dmax,


max_it (40), number of parameters (nvars = 4), LB =0.1, UB=1.0.

125
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

b. Generate random population as Eq. 4.19 subject to constraints of Eq.


4.31.

c. For all population species, extract new probability density functions for
foreground and background according to Eq. 4.15 and 4.16.

d. Perform equalization of foreground and background separately


according to Eq. 4.17 and Eq. 4.18.

e. Find values of individual objective functions and combine these to


calculate the cost of population species according to Eq. 4.29.

f. Sort the population according to cost. Assign first/best candidate as sea


and perform initialization of rivers and streams accordingly.

g. Designate streams to rivers and sea according to Eq. 4.20.

h. Model flow of streams to rivers and rivers to sea according to Eq. 4.21
and 4.22 and generate new positions for streams and rivers.

i. Exchange positions of river with stream and exchange position of sea


with river if better solutions are available (Figure 4.2).

j. Perform evaporation process according to Eq. 4.23 and in case


evaporation condition is satisfied, also perform raining process
according to Eq. 4.25.

k. Update using Eq. 4.24.

l. Check for convergence, if stopping criteria is met, use value of sea as


best solution else return to step 5(f).

6. Use the optimal values extracted by WCA to generate enhanced Y channel


image.

7. Combine CbCr channel information into enhanced Y channel and convert


back to RGB space.

The above algorithm inputs image or frame in first step and as part of pre-processing
operation extracts Y channel of image after converting from RGB space to YCbCr
colour space. The input image is segmented into foreground and background sub-
images using two dimensional Ostu‘s thresholding principle (step 3, step 4). Two
dimensional Ostu‘s method has been utilized as it is more suitable to complex or

126
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

natural images. Both sub images are enhanced separately by subjecting probability
density functions of foreground and background to specifically designed constraints.
The designed constraints can be controlled with four parameters (q,r,s,t) as illustrated
in previous sections. Different combinations of these parameters will constitute for
different enhanced versions of final image and in order to select an optimal value,
water cycle algorithm has been used (Step 5). WCA first generates a random
population of raindrops (stream) within fixed lower and upper bound. The algorithm
then proceeds to initialize sea, rivers and streams from initial population. Flow of
streams to rivers and rivers to sea is modelled for fixed number of iterations and best
solutions are re-designated as sea or rivers. The objective function for water cycle
optimization is considered to be a three dimensional function that tends to enhance
contrast and preserve brightness and colourless of input image. The best solution is
utilized for modification of foreground and background sub-images which are
eventually combined to generate final enhanced Y channel image. The CbCr
components are added to the enhanced Y channel image to get the final image.

4.5 RESULTS AND DISCUSSION


Testing of any approach is a challenging task and in order to evaluate performance of
proposed method, different levels of experiments were designed in different domains.
The first evaluation of proposed method was done on standard datasets of computer
vision and image processing. Second level of experiment was conducted on hazy and
unclear images downloaded from datasets available at [243]. In addition, the proposed
method was also tested on hazy videos as used by [244], and object detection videos
from CAVAIR dataset. The frames or images were subjected to proposed approach
for 40 iterations and best obtained results are reported. In order to compare
performance of proposed algorithm, same images were enhanced with contemporary
techniques like Histogram Equalization (HE), BBHE (Bi-level histogram
equalization), CLAHE (contrast limited histogram equalization) and RMSHE. The
results have been presented in terms of human visual perception and qualitative
measures like entropy, edge based contrast, colourfulness, contrast improvement
index (cii), MSE and PSNR have also been evaluated. Although tests were conducted
on about 1000 images and twenty different videos with more than 40000 frames, we
hereby demonstrate some of the results under all categories of experiments. The major
focus is on colour, complex and natural images.

127
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

(a) (b)

(c) (d)

(e) (f)
Figure 4-3 Comparison of enhancement results on Lenna image (a) Original image, (b)
HE, (c) BBHE, (d) CLAHE, (e) RMSHE, (f) Proposed method
The first test was conducted on standard Lenna image and obtained results are
presented in Figure 4.3. It is clear from the figure that HE was not able to preserve

128
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

original color of image and over-enhances it as shown in Figure 4.3(b). The results
obtained by CLAHE and RMSHE in Figure 4.3 (d) and Figure 4.3 (e) are almost same

(a) (b)

(c) (d)

(e) (f)
Figure 4-4 Comparison of enhancement results on camel and desert image (a) Original
image, (b) HE, (c) BBHE, (d)CLAHE, (e) RMSHE, (f) Proposed method

129
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

and both these techniques were not able to remove haziness from original image.
Improved results are shown for BBHE (Figure 4.3 (c)) but it can be seen that BBHE
was not able to preserve texture of hair and cream colour in background has been
converted to white. The results of the proposed method are shown in Figure 4.3 (f)
and it can be observed that proposed method was not only able to provide a contrast
rich image but colour and details of image were also preserved. The final obtained
image is more natural, colourful and visually pleasing.

Second level of experiments was performed on images picked from Berkely


university dataset. Sample complex and natural images have been picked and results
are demonstrated here. In Figure 4.4, it can be seen that none of the contemporary
technique was able to perform enhancement of the camel image effectively. The
results produced by HE and BBHE resulted in complete loss of details with undesired
white spots being added to the original image because of over enhancement made by
HE and BBHE have over enhanced the image. Results of CLAHE and RMSHE,
Figure 4.4(d) and Figure 4.4(e), are better but artifacts can still be observed in results
of these techniques. The colour of camel seat has been turned to black by HE, BBHE
and RMSHE. The results of CLAHE are better than these methods however CLAHE
was not able to perform enhancement of regions with high intensity values. The results
of proposed method are much appreciable as compared to these methods.

Figure 4.5 shows results of various algorithms for foggy bench image. It can be seen
that original color of sand and grass are lost after performing enhancement using HE,
BBHE, CLAHE and RMSHE methods. Some white spots can be observed on portions
of image covering bench in HE, BBHE and RMSHE which signals over enhancement
but no such spot could be traced in final image generated by proposed technique.
(Figure 4.5(f)). There is also some portion of the ground for which color of soil has
been changed by all techniques where as no such change can be observed in the
results of proposed method. This is because proposed method converts image from
RGB to YCbCr which helps to preserve color details. Suitably designed objective
function has also resulted in controlled enhancement with no side effects. This
indicates that enhancement made by proposed technique is controlled and no side
effects can be observed. The enhanced image looks rich in contrast and haziness has
been removed from background in a far better way than any of the other methods. In
Figure 4.6, a redundant bright spot has been generated in background for HE and

130
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

BBHE methods signaling over enhancement of source image. In addition HE, BBHE
and RMSHE were not able to perform enhancement of lower sub areas of image.
Results of CLAHE and proposed method seem to be comparable however proposed

(a) (b)

(c) (d)

(e) (f)
Figure 4-5 Comparison of enhancement results on foggy bench image(a) Original image,
(b) HE, (c) BBHE, (d) CLAHE, (e) RMSHE, (f) Proposed method

131
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

(a) (b)

(c) (d)

(e) (f)
Figure 4-6 Comparison of enhancement results on Tienamen image (a) Original image,
(b) HE, (c) BBHE, (d) CLAHE, (e) RMSHE, (f) Proposed method
method was able to preserve colors of the source image which was not the case with
CLAHE. It is because of the objective function implemented by proposed algorithm
which makes sure that brightness and colorfulness of input image are maintained.

132
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

(a) (b)

(c) (d)

(e) (f)
Figure 4-7 Comparison of enhancement results on aircraft image (a) Original image,
(b) HE, (c) BBHE, (d) CLAHE, (e) RMSHE, (f) Proposed method
Figure 4.7 depicts results obtained for various algorithms for aircraft image. It can be
observed that proposed method was able to preserve details of aircraft while others
algorithms have failed completely. Techniques like HE, BBHE and RMSHE have
completely failed in rendering any enhancement to the source image. The results of

133
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

proposed technique are quite appreciable as proposed algorithm uses three different
functions to extract ideal values of parameters for controlling enhancement.

Figure 4.8 depicts another instance of the failure of contemporary techniques like HE,
BBHE, RMSHE to provide enhancement in foggy environment. These techniques
were not able to enhance regions that are far away from the source; in addition color
information of truck is also lost in HE and BBHE methods. Results of CLAHE seem
to be better but whiteness and artifacts can be seen in portions of image. The results of
proposed technique are much better than all other techniques.
The proposed method was also tested for enhancement of video frames from
CAVAIR dataset. Such sequences were downloaded from [162]. This section is
devoted to discussion on the results obtained for these videos. We first present visual
results obtained on CAVIAR dataset. CAVIAR dataset consists of object detection
and tracking videos captured inside university campus. More details about the
CAVIAR and other datasets have been discussed in Chapter 2.

(a) (b)

(c) (d)

134
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

(e) (f)
Figure 4-8 Comparison of enhancement results on foggy bus image (a) Original
image, (b) HE, (c) BBHE, (d) CLAHE, (e) RMSHE, (f) Proposed method
Figure 4.9 and 4.10 projects obtained results on C2 and br3 videos of CAVAIR
dataset. Results of all methods are appreciable in. this may be attributed to the fact
that C2 is indoor video without any noise. In Figure 4.10, results of proposed

(a) (b)

(c) (d)

135
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

(e) (f)
Figure 4-9 Comparision of enhancement results on frame #246 of c2 video (a) Original
image, (b) HE, (c) BBHE, (d) CLAHE, (e) RMSHE, (f) Proposed method
technique are found to be better than all methods. The areas in top right corner of
frame were also enhanced which was not the case with contemporary techniques.

(a) (b)

(c) (d)

136
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

(e) (f)
Figure 4-10 Comparison of enhancement results on Frame #3 of br3 video (a) Original
image, (b) HE, (c) BBHE, (d) CLAHE, (e) RMSHE, (f) Proposed method
In order to access performance levels of the proposed technique, it was decided to test
it on hazy sequences, hazeroad and riverside. The hazeroad video sequence is of 60

(a) (b)

(c) (d)

137
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

(e) (f)
Figure 4-11 Comparision of enhancement results on frame# 55 of hazeroad video (a)
Original image, (b) HE, (c) BBHE, (d) CLAHE, (e) RMSHE, (f) Proposed method
sec. duration with frame dimensions of 720 x 400, total frames =1500 captured at 25
frames per second. The riverside video sequence is of 20 sec. duration, frame
dimensions 640 x 480, 24 frames per second with total 489 frames. The visual results
of different algorithms on frames#55 and frame#200 of hazeroad video sequence are
shown in Figure 4.11 and Figure 4.12 respectively. It can be clearly seen that
contemporary techniques were not able to enhance regions which are far from the
capturing camera. The proposed technique is able to remove the hazy effects in the
video more effectively than all the methods. The output frames are much clear and
sharper than other methods; this is because of the adaptive nature of proposed
technique. The appearance of road and sign boards is much fine in Figure 4.11(f)
because proposed method is able to preserve details of frames.

(a) (b)

138
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

(c) (d)

(e) (f)
Figure 4-12 Comparision of enhancement results on frame# 4 of riverside video (a)
Original image, (b) HE, (c) BBHE, (d) CLAHE, (e) RMSHE, (f) Proposed method
Figure 4.13 and Figure 4.14 presents results obtained on frames 4 and 154 for
riverside hazy video sequence. The results of proposed method are better than all
contemporary technique which justifies its applicability to hazy videos also.

(a) (b)

139
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

(c) (d)

(e) (f)
Figure 4-13 Comparision of enhancement results on frame# 154 of riverside video(a)
Original image, (b) HE, (c) BBHE, (d) CLAHE, (e) RMSHE, (f) Proposed method
4.5.1 Quantitative Results of Proposed Method

Apart from visual results depicted in previous paragraphs, the quality of test images
and frames enhanced using various algorithms shall also be measured quantitatively
using some statistical measures. A number of parameters could be used for this
purpose and some of these have been utilized in this study. Since the proposed study
aims to enhance contrast, preserve details and colourfulness therefore parameters like
discrete entropy, edge based contrast, contrast improvement index, colourfulness,
MSE and PSNR has been used for evaluating proposed technique. Tables 4.1-4.6
demonstrates values of these parameters as obtained on different algorithms. Discrete
Entropy is a useful parameter for measuring details of any image and measures
information content in an image after enhancement. It is useful measure for measuring
image quality and can be measured using Eq. 4.31

140
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

( ) ∑ ( ) ( ) (4.31)

The value of discrete entropy shall increase desirably and an algorithm is termed as
good when it is able to preserve or minimize change in the value of discrete entropy
of original and enhanced frame. In Table 4.1 describes values of discrete entropy for
various test images/ frames used in this study. It is seen that proposed algorithm either
increased value of entropy of an image or maintain same magnitude as original. This
means that the details of source image were preserved by objective function and
results are encouraging.

Table 4-1 Comparison of discrete entropy values for various algorithms


Sr. Image Original HE BBHE CLAHE RMSHE Proposed
No

1. Lenna 5.51955 7.07394 7.14725 6.83556 6.24508 7.21614

2. Camel 6.92767 7.41832 7.42756 7.55185 7.78121 7.52567

3. foggy bench 7.41689 7.36125 7.39041 7.48466 7.8954 7.76138

4. Tienamen 7.64235 7.22936 7.30205 7.60426 7.68047 7.69592

5. Aircraft 6.23429 6.88136 6.98299 6.95618 6.99534 6.55078

6. foggy bus 7.10801 7.29976 7.4575 7.39229 7.54153 7.43937

7. Mountains 7.17124 7.21629 7.23563 7.3936 7.36526 7.29593

8. haze weather 7.26217 7.33521 7.46763 7.31939 7.33572 7.54303

9. foggy trees 7.42706 7.3476 7.31067 7.72052 7.79199 7.27353

10. foggy forest 6.05695 6.17036 6.21145 6.25049 6.24546 6.27028

11. foggy house 7.15261 7.17026 7.24065 7.27145 7.2928 7.28179

12. frame#24 of c2 7.2487 7.4217 7.4158 7.3874 7.45717 7.41278

13. frame#98 of c2 7.18779 7.2789 7.3478 7.3571 7.38745 7.37469

14. frame#308 of c2 7.29461 7.3849 7.4973 7.51261 7.56145 7.7156

15. frame #3 of br3 7.2608 7.3564 7.4908 7.5527 7.7714 7.7812

16. frame#43 of br3 7.1689 7.2578 7.26897 7.3147 7.35429 7.3636

17. frame#55 of 7.1686 7.0578 7.3737 7.5412 7.3526 7.3645


hazing road

141
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

18. Frame#200 of 7.0059 7.1083 7.1635 7.1780 7.20145 7.2377


hazing road

19. Frame#359 of 7.1598 7.2192 7.2235 7.6321 7.4172 7.5874


hazing road

20. Frame#4 of 6.6167 7.2416 7.2574 7.2854 7.2904 7.2920


Riverside video

21. Frame#154 of 6.6270 7.2513 7.2598 7.2932 7.2957 7.2991


Riverside video

22. Frame#483 of 6.6286 7.2431 7.2941 7.2904 7.3102 7.2280


Riverside video
Table 4-2 Comparison of edge based contrast values for various algorithms
Sr. Image Original HE BBHE CLAHE RMSHE Proposed
No

1. Lenna 45 41.81753 43.4148 54.66605 53.6942 57.53099

2. Camel 13.1660 36.04692 30.3782 25.40675 29.3226 47.37631

3. foggy bench 53.2507 43.39474 52.3727 43.39441 54.8284 55.08023

4. Tienamen 50.2959 40.49902 44.82648 48.77289 45.913 51.12503

5. Aircraft 39.25515 42.18912 51.00271 48.18964 49.1758 48.579

6. foggy bus 7.10801 7.29976 7.4575 7.39229 7.54153 7.4393

7. Mountains
38.6174 40.7504 37.4932 42.65657 38.3540 45.3334

8. haze weather 47.6681 41.47838 48.3034 53.19276 46.3324 55.1931

9. foggy trees 19.6066 46.0364 30.5084 38.82107 30.9291 42.5789

10. foggy forest 43.8431 44.2145 44.6578 46.5748 46.9745 46.1464

11. foggy house 42.7601 46.1289 47.3589 44.7891 46.7896 48.0278

12. frame#24- c2 39.4780 41.3717 45.576 44.0139 45.746 45.789

13. frame#98- c2 40.7203 46.256 47.7512 47.5486 49.1025 48.5193

14. frame#308-c2 39.3733 43.546 44.0569 46.685 46.0324 47.144

15. frame #3- br3 32.4323 36.7071 32.8179 39.412 33.1266 39.487

16. frame#43-br3 31.259 37.4531 34.1023 39.53 37.4896 39.153

142
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

17. frame #55-


hazing road 40.8643 40.2576 40.1619 39.8530 45.3518 43.8153

18. Frame#200 - 41.2578 46.2789 47.1258 48.369 48.0147 49.452


hazing road

19. Frame#359- 41.729 45.7450 46.8941 49.7456 49.1547 48.7956


hazing road

20. Frame#4- 44.6753 41.14527 33.2169 44.79291 42.1878 33.21697


Riverside

21. Frame#154 44.4242 41.05486 34.2649 44.67718 42.0123 34.26496


of Riverside

22. Frame#483 44.5905 41.20857 34.3727 44.90438 42.1678 34.37273


of Riverside

Another important measure of image quality is the contrast or relative increase in


contrast of enhanced image or frame. Edge based contrast measured by combining
different parameters like edge based intensity, entropy, edge pixels were used and
measured using Eq. 4.27. The observed values are presented in table 4.2.

Table 4-3 Comparison of cii values for various algorithms


Sr. Image Original HE BBHE CLAHE RMSHE Proposed
No

1. Lenna 1.000 1.4521 1.35789 2.417621 1.566949 3.49328

2. Camel 1.000 0.1897 0.21056 2.166294 1.797936 2.602408

3. foggy bench 1.000 1.5781 0.9874 2.12056 2.054997 2.37136

4. Tienamen 1.000 1.1689 1.1789 2.013815 1.181047 2.134998

5. Aircraft 1.000 1.0178 1.2713 1.561 1.705542 1.344101

6. foggy bus 1.000 0.94785 0.9268 1.302322 0.85533 1.443819

7. mountains 1.000 0.00456 0.00712 0.189981 0.121619 0.144246

8. haze weather 1.000 0.0896 0.10489 2.064851 1.226329 2.001621

9. foggy trees 1.000 0.03147 0.03258 1.396552 1.678399 1.672023

10. foggy forest 1.000 0.0309 0.0447 0.0512 0.0661 0.0712

11. foggy house 1.000 0.0349 0.0474 0.0686 0.0736 0.0766

12. frame#24-c2 1.000 0.21527 0.19934 0.18214 0.1579 0.08589

143
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

13. frame#98- c2 1.000 0.22049 0.20265 0.18702 0.16066 0.2447

14. Frame#308-c2 1.000 0.21796 0.19891 0.18893 0.15666 0.08784

15. frame #3- br3 1.000 0.0192 0.0574 1.6982 1.69054 2.1789

16. frame #43 -br3 1.000 0.0256 0.0416 1.2351 1.3245 1.5974

17. frame #55 - 1.000 0.00124 0.00256 0.0897 0.0344 0.1025


hazing road

18. Frame#200- 1.000 0.00546 0.00814 0.0846 0.0753 0.0975


hazing road

19. Frame#359- 1.000 0.00325 0.00726 0.00853 0.0746 0.0814


hazing road

20. Frame#4 - 1.000 0.03746 0.14 0.13535 0.07644 0.05788


Riverside

21. Frame#154 1.000 0.03824 0.14312 0.13583 0.07871 0.05923


Riverside

22. Frame#483 - 1.000 0.03783 0.13986 0.13293 0.07734 0.05588


Riverside

contrast improvement index(cii) parameter is used in order to further measure contrast


of image. Its formula can be expressed as:

(4.32)

where contrasts of original and outputted image are given as and


. The value of C is calculated by using local region contrast which can be
calculated as

(4.33)

where Xf and Xb are maximum and minimum luminance values of foreground and
background regions in local window size of 5*5. Higher value of cii represents better
image quality. Values of cii reported in this study have been normalized according to
image size to make them meaningful. Table 4.3 lists values of cii obtained for various
methods, value of cii for original image comes to be 1. Observing tables 4.2 and 4.3,
it is clear that proposed approach was able to enhance the contrast of almost all
images effectively. The values of cii observed for almost all frames and videos show
an improvement as compared to other methods. This is because of the fact that the

144
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

Table 4-4 Comparison of colorfulness values for various algorithms


Sr. Image Original HE BBHE CLAHE RMSHE Proposed
No
1. Lenna 17.2714 17.2619 16.5929 17.2256 17.26335 18.0018

2. Camel 39.9830 36.4172 37.0909 39.8726 39.9964 40.0343

3. foggy bench 16.3323 15.1656 15.5917 15.0338 16.06058 16.2971

4. Tienamen 31.8471 31.825 33.4687 31.8983 31.88933 31.924

5. Aircraft 12.5687 11.947 12.5974 12.5517 12.4877 12.5748

6. foggy bus 7.50751 8.0718 8.07778 8.11048 8.11322 8.1755

7. mountains 41.7874 42.8050 42.7777 41.9980 41.8426 42.971

8. haze weather 11.2910 13.154 13.0575 11.5282 11.5338 11.539

9. foggy trees 20.6650 21.7223 21.9232 21.0708 20.7415 21.931

10. foggy forest 17.8313 18.125 18.5978 19.8790 21.004 20.711

11. foggy house 9.2712 10.785 11.289 12.0458 13.145 13.578

12. frame#24 -c2 24.1756 26.463 26.8795 27.8982 26.7846 27.912

13. frame#98- c2 25.4789 25.1423 26.9973 27.9191 26.7569 27.841

14. Frame#308-c2 30.4210 33.2436 33.0107 34.3094 35.9874 35.991

15. frame #3 -br3 18.1431 16.3281 16.684 17.5015 17.3402 17.575

16. frame #43br3 18.2697 20.1456 21.0145 26.3489 26.1925 27.345

17. frame #55 14.952 15.0578 15.870 15.0322 14.8658 15.791


hazing road

18. Frame#200 15.4331 16.506 16.58149 15.97997 15.95033 15.971


hazing road

19. Frame#359 15.1024 5.000 16.31303 15.30723 15.42613 15.273


hazing road

20. Frame#4 of 8.0924 7.4772 8.21477 7.94143 8.12705 8.074


Riverside

21. Frame#154- 8.2453 7.61897 8.36551 8.0604 8.22534 8.229


Riverside

22. Frame#483- 8.22051 7.57482 8.3356 8.04319 8.21101 8.214


Riverside

145
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

objective function used in proposed method tends to increase contrast without any
multiplicative index as compared to other functions. This eventually leads to rise in
the observed values. The table depicts an increase in values of contrast and cii over
other methods suggesting effectiveness of proposed algorithm.

Colourfulness is also an important measure for measuring quality of output frame.


Any enhancement algorithm shall be able to preserve colourfulness of original image.
To measure colourfulness of output frame, [242] has used a psychophysical category
scaling experiment to devise an effective measure for colourfulness. They rated
images according to seven categories of colorfulness. A suitable metric was then
designed to fit the results with maximal correlation.

The metrics utilizes simple opponent color space

( )
(4.34)

The used metrics assumes image is coded in the sRGB color space and measures
colorfulness metric as:

̂ √ √ (4.35)

where standard deviation and the mean value of the pixel is given by σ and µ. The
colorfulness can then be specified as

̂ ̂ ̂ (4.36)

where original colorfulness estimate and outputted colorfulness estimate of images is


given by ̂ and ̂ .

The values of colourfulness have been tabulated in Table 4.4. The effectiveness of the
proposed algorithm in preserving colour of original frame is also justified when we
observe the values obtained for various test images and frames. The proposed method
is efficient in terms of improving colourfulness for almost all images barring a few,
even in those values observed values are rather competitive. The observed values in
shows that original values of images and frames are either preserved or enhanced
suitably in addition to enrichment of contrast values and preserving details. This is
because proposed multi objective function considers colourfulness as one of input
variable in which difference between original and enhanced image is used. It helps to
keep colourfulness of test frames in check and prevent any loss in naturalness. The

146
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

Table 4-5 Comparison of MSE values for various algorithms


Sr. Image HE BBHE CLAHE RMSHE Proposed
No

1. Lenna 132.5898 124.3801 98.82253 0.39547 92.5898

2. Camel 88.74955 114.2815 49.70072 87.68683 14.22405

3. foggy bench 153.7654 112.5811 160.3484 103.735 117.9389

4. Tienamen 141.6714 113.3389 49.79701 146.0021 36.81183

5. Aircraft 108.5361 80.846 26.72487 67.24598 26.73755

6. foggy bus 110.9421 111.0487 101.3295 84.71749 86.3038

7. mountains 67.20057 110.2334 45.5466 28.22699 57.80656

8. haze weather 131.6577 86.45403 23.69154 26.67682 15.70304

9. foggy trees 56.75089 127.6994 32.06301 113.961 50.5162

10. foggy forest 84.9971 92.358 81.257 80.71 83.8512

11. foggy house 98.2568 96.278 89.674 90.459 87.126

12. frame#24 -c2 75.7022 77.5044 82.1847 71.579 49.3589

13. frame#98- c2 89.2479 77.5128 82.1890 70.6987 64.7563

14. Frame#308-c2 105.698 77.8879 81.9294 85.459 58.2478

15. frame #3 -br3 42.33627 38.26135 58.00527 39.60448 37.25039

16. frame #43br3 55.99224 53.23413 68.88865 55.75625 45.12705

17. frame #55 0.09362 0.10573 0.12556 0.07266 0.12966


hazing road

18. Frame#200 0.11259 0.13026 0.1358 0.09206 0.06787


hazing road

19. Frame#359 0.08108 0.08088 0.10349 0.06029 0.04351


hazing road

20. Frame#4 5.78018 36.6773 4.45227 4.37417 10.57793


Riverside

21. Frame#154- 32.156 6.34278 25.16102 4.83622 1.73002


Riverside

22. Frame#483- 42.456 12.10671 115.6426 11.33176 10.28134


Riverside

147
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

Table 4-6 Comparison of PSNR values for various algorithms


Sr. Image HE BBHE CLAHE RMSHE Proposed
No

1. Lenna 26.9397 27.21729 28.21624 52.19731 28.46517

2. Camel 28.68314 27.58505 31.2012 28.7355 36.60057

3. foggy bench 26.29622 27.65015 26.11417 28.00555 27.41423

4. Tienamen 26.65202 27.62104 31.19285 26.52125 32.47093

5. Aircraft 27.80936 29.08868 33.89567 29.88823 33.85959

6. foggy bus 27.71385 27.70968 28.10757 28.88507 28.7705

7. Mountains 29.91631 27.75003 31.58071 33.65871 30.51103

8. haze weather 26.97034 28.79695 34.41893 33.90347 36.17097

9. foggy trees 30.62668 27.10305 33.10642 27.59737 31.0965

10. foggy forest 28.598 32.014 39.157 31.752 39.912

11. foggy house 36.189 38.945 41.289 40.587 42.368\

12. frame#24 -c2 43.6483 40.80531 41.03953 39.59712 41.57477

13. frame#98- c2 43.16579 41.29244 41.40049 40.81247 41.70511

14. Frame#308-c2 41.67435 40.63348 40.64413 38.93462 40.89007

15. frame #3 -br3 33.61059 31.8978 32.33801 30.53014 32.19016

16. frame #43br3 32.0226 30.78129 31.01488 29.83478 30.83442

17. frame #55 36.06597 32.52047 33.21835 31.53524 34.51668


hazing road

18. Frame#200 37.9548 27.47594 29.18156 28.52884 29.9606


hazing road

19. Frame#359 36.34535 33.05724 33.44329 30.8029 33.70205


hazing road

20. Frame#4 50.05257 40.54556 32.52088 41.67917 41.75704


Riverside

21. Frame#154- 49.1648 40.14253 34.15781 41.32026 45.78866


Riverside

22. Frame#483- 44.41886 37.33463 27.53362 37.62187 38.04469


Riverside

148
CHAPTER 4
MULTI OBJECTIVE WATER CYCLE ALGORITHM BASED IMAGE ENHANCEMENT

values depicted in table shows that the proposed method is justified for preserving
colourfulness of original image as obtained results are quite promising. The observed
values show considerable improvement over other contemporary methods.
MSE and PSNR measures borrowed from signal processing have also been used
historically for evaluation of image quality. Although their findings cannot be
considered reliable nevertheless, their use is still common practice and for the sake of
completeness these have also been included in our study. Tables 4.5 and 4.6 enlist
values of MSE and PSNR for test images respectively. The mean square
error(MSE) between two images I(i, j) and J(i,j) of size (M x N) can be defined as:

∑ ∑ , ( ) ( )- (4.37)

Since MSE depends strongly on image intensity scaling (number of bits used for
single pixel), therefore Peak-signal to Noise Ration (PSNR) measure is used, which is
calculated as

⁄ (4.38)

where L reflects the maximum value of a pixel; high signal to noise ratio will be
generated for a small value of mean square error. More similarity between original
and final image will result in 4.5 and 4.6 minimization of MSE parameter and
enhancement of PSNR parameter. Tables suggest that the outputted values of
proposed technique are in correlation to the values for other parameters. Tables show
that values of MSE have decreased as compared to other methods and values of PSNR
have been increased. It justifies that proposed method was successful in reducing the
error in the processed frame.

4.6 CHAPTER SUMMARY


This chapter was devoted to discussions on the need and utilization of contrast
enhancement of videos dedicated to object detection and tracking. The chapter has
discussed various approaches used in pre-processing of video with a focus on contrast
enhancement methods. Various traditional and soft computing based contrast
enhancement measures have been discussed extensively. Role of soft computing
techniques in controlling and enhancing powers of traditional soft computing methods
have been discussed. The chapter has presented an evolutionary approach based on
water cycle algorithm for enhancement of images and videos. The proposed method
performs a pre-processing operation on input video sequence and then runs a

149
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

controlled version of histogram equalization for contrast stretching. Enhancement is


controlled by utilizing powers of WCA for finding an optimal combination of
variables according to image operations. These variables have been used in a suitably
designed multi-objective function. The multi-objective function has been designed to
prevent loss of colourfulness and truncation of pixel values during enhancement
process. The function encourages enhancement of contrast simultaneously preserving
details and richness of image. The generated images are better in colour and contrast.
In order to test effectiveness of proposed technique, different experiments were
designed on standard, natural or complex and hazy videos. Along with visual
presentation of results, a number of quality measurement parameters were also
evaluated. After exhaustive evaluations, it was shown that the proposed technique
leads in overall performance as compared to various other methods. The obtained
results were appreciable both in qualitative and quantitative parameters and
demonstrated capabilities of proposed technique in removing haze effects and
preserving colourfulness and brightness of original frames.

150
ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS

You might also like