ISSN (Print) : 2319-5940

ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 3, March 2013

Various Image Enhancement Techniques- A Critical Review

S.S. Bedi1, Rati Khandelwal2
Assistant Professor, CSIT, MJPRU, Bareilly, India 1
M.Tech IVth Semester, Student, Banasthali Vidyapith, Jaipur, India 2

ABSTRACT: Image Enhancement is one of the most important and difficult techniques in image research. The aim of image
enhancement is to improve the visual appearance of an image, or to provide a “better transform representation for future automated image
processing. Many images like medical images, satellite images, aerial images and even real life photographs suffer from poor contrast
and noise. It is necessary to enhance the contrast and remove the noise to increase image quality. One of the most important stages in
medical images detection and analysis is Image Enhancement techniques which improves the quality (clarity) of images for human
viewing, removing blurring and noise, increasing contrast, and revealing details are examples of enhancement operations. The
enhancement technique differs from one field to another according to its objective. The existing techniques of image enhancement can be
classified into two categories: Spatial Domain and Frequency domain enhancement. In this paper, we present an overview of image
enhancement processing techniques in spatial domain. More specifically, we categorise processing methods based representative
techniques of Image enhancement. Thus the contribution of this paper is to classify and review image enhancement processing
techniques, attempt an evaluation of shortcomings and general needs in this field of active research and in last we will point out
promising directions on research for image enhancement for future research.

Keywords: Frequency based domain enhancement, Image Enhancement, Spatial based domain enhancement, Histogram Equalization.

I. INTRODUCTION

Image enhancement problem can be formulated as follows: given an transformed domain properties. The basic limitations including are it
input low quality image and the output high quality image for specific cannot simultaneously enhance all parts of image very well and it is
applications. It is well-known that image enhancement as an active also difficult to automate the image enhancement procedure. In this
topic in medical imaging has received much attention in recent years. paper according to if enhanced image embed high quality background
The aim is to improve the visual appearance of the image, or to information, the existing techniques of image enhancement like
provide a “better” transform representation for future automated spatial domain methods can again be classified into two broad
image processing, such as analysis, detection, segmentation and categories: Point Processing operation and Spatial filter operations.
recognition. Moreover, it helps analyses background information that Traditional methods of image enhancement are to enhance the low
is essential to understand object behaviour without requiring quality image itself. It doesn’t embed any high quality background
expensive human visual inspection. Carrying out image enhancement information. The reason is that in the dark image, some areas are so
understanding under low quality image is a challenging problem dark that all the information is already lost in those regions. No matter
because of these reasons. Due to low contrast, we cannot clearly how much illumination enhancement you apply, it will not be able to
extract objects from the dark background. Most colour based methods bring back lost information. Frequency domain methods can again be
will fail on this matter if the colour of the objects and that of the classified into three categories: Image Smoothing, Image Sharpening,
background are similar. The survey of available techniques is based Periodic Noise reduction by frequency domain filtering. In this paper
on the existing techniques of image enhancement, which can be we focus on image enhancement considering areas of spatial domain
classified into two broad categories: Spatial based domain image enhancement techniques. The remainder of the paper is organized as
enhancement and Frequency based domain image enhancement. follows. Section 2 gives brief overview of some related work, in
Spatial based domain image enhancement operates directly on pixels. Section 3 review of spatial domain will be discussed, Section 4 gives
The main advantage of spatial based domain technique is that they some applications and the proposed future directions and Section 5
conceptually simple to understand and the complexity of these conclude the paper.
techniques is low which favours real time implementations. But these
techniques generally lacks in providing adequate robustness and
imperceptibility requirements. Frequency based domain image II. RELATED WORK
enhancement is a term used to describe the analysis of mathematical
functions or signals with respect to frequency and operate directly on Image enhancement process consists of a collection of techniques that
the transform coefficients of the image, such as Fourier transform, seek to improve the visual appearance of an image or to convert the
discrete wavelet transform (DWT), and discrete cosine transform image to a form better suited for analysis by a human or machine. The
(DCT). The basic idea in using this technique is to enhance the image principal objective of image enhancement is to modify attributes of an
by manipulating the transform coefficients. The advantages of image to make it more suitable for a given task and a specific
frequency based image enhancement includes low complexity of observer. During this process, one or more attributes of the image are
computations, ease of viewing and manipulating the frequency modified. Digital Image enhancement techniques provide a multitude
composition of the image and the easy applicability of special of choices for improving the visual quality of images. Appropriate
Copyright to IJARCCE www.ijarcce.com 1605
 ISSN (Print) : 2319-5940
ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 3, March 2013

choice of such techniques is greatly influenced by the imaging

Original Image Negative
modality, task at hand and viewing conditions. A familiar example of
enhancement is in which when we increase the contrast of an image
and filters it to remove the noise "it looks better". It is important to
keep in mind that enhancement is a very subjective area of image
processing. Improvement in quality of these degraded images can be
achieved by using application of enhancement techniques.
The work done by various researchers for Image Enhancement are
discussed here, Madhu[1] suggested that the Adaptive histogram Fig. 1. Original image and its negative image
equalization produced a better result, but the image is still not free
from washed out appearance. The sharpness is poor and the Another technique is Image Thresholding transformation in which let
background information as well as the plane is still fogged and poor rth be a threshold value in f(x, y). Image thresholding can be achieved
in contrast. Alpha rooting rendered the entire image in a dark tone. as in a normalized gray scale As pixel values of threshold image are
Even the outline of the clouds which was visible in case of histogram either 0’s or 1’s, g(x, y) is also named as binary image. These are
equalization is lost. Agaian [2] suggested that the common no particularly useful in image segmentation to isolate an image of
transform-based enhancement technique is global histogram interest from back ground. Moon image can be isolated from black
equalization, which attempts to alter the spatial histogram of an image ground in binary image as shown in Fig 2.
to closely match a uniform distribution. Histogram equalization
suffers from the problem of being poorly suited for retaining local
detail due to its global treatment of the image. It is also common that
the equalization will over enhance the image, resulting in an
undesired loss of visual data, of quality and of intensity scale. Tang
[3] suggested global histogram equalization, which adjusts the
intensity histogram to approximate uniform distribution. The global
histogram equalization is that the global image properties may not be
appropriately applied in a local context. In fact, global histogram Fig 2. Original Image and its threshold Image
modification treats all regions of the image equally and, thus, often
Next kind of transformation is the Log transformation which maps a
yields poor local performance in terms of detail preservation.
narrow range of low gray levels into a wider range of gray levels i.e.
Therefore, several local image enhancement algorithms have been
expand values of bright pixels and compress values of dark pixels. If
introduced to improve enhancement.
C is the scaling factor, then log transformation can be achieved as s =
C log (1+│r│). Logarithmic image of a cameraman reveal more
III. SPATIAL DOMAIN METHODS
detail as shown in Fig.3.

Spatial domain techniques directly deal with the image pixels. The
pixel values are manipulated to achieve desired enhancement. Spatial
domain techniques like the logarithmic transforms, power law
transforms, histogram equalization are based on the direct
manipulation of the pixels in the image. Spatial techniques are
particularly useful for directly altering the gray level values of
individual pixels and hence the overall contrast of the entire image.
But they usually enhance the whole image in a uniform manner which
in many cases produces undesirable results. It is not possible to Fig. 3 DFT of image and its logarithmic
selectively enhance edges or other required information effectively.
Techniques like histogram equalization are effective in many images.
The approaches can be classified into two categories: Point Inverse logarithmic transformations map a wide range of gray level
Processing operation (Intensity transformation function) and Spatial values into a narrow range of gray level values i.e. expand values of
filter operations. An overview of some of the well known methods is dark pixels and compresses values of bright pixels. Log and inverse
discussed here. Point processing operations (Intensity transformation log operations are particularly used when gray level values of an
function) is the simplest spatial domain operation as operations are image have extremely large range and small range respectively.
performed on single pixel only. Pixel values of the processed image Logarithmic Transformations can be used to brighten the intensities
depend on pixel values of original image. It can be given by the of an image (like the Gamma Transformation, where gamma < 1).
expression g(x,y) = T[f(x,y)] , where T is gray level transformation in More often, it is used to increase the detail (or contrast) of lower
point processing. The Point processing approaches can be classified intensity values. They are especially useful for bringing out detail in
into four categories as Image Negatives in which gray level values of Fourier transforms. In Power Law (Gamma) transformation the
the pixels in an image are inverted to get its negative image. Consider relation between pixel values of f(x, y) and g(x, y) in this
a 8 bit digital image of size M x N, then each pixel value from transformation is given by s =c r γ , where c and γ are positive
original image is subtracted from 255 as g (x, y)=255- f(x, y) for 0 ≤ constants. If γ < 1 power law transformation maps a narrow range of
x < M and 0 ≤ x < N. In a normalized gray scale, s = 1.0 – r. Negative dark pixel values into a wider range and wider ranges of bright pixel
images are useful for enhancing white or gray detail embedded in values to a narrow range. Family of possible transformations on
dark regions of an image. Fig.1 shows an example of an image varying γ with c=1 is shown in Fig.4.
negative.

Copyright to IJARCCE www.ijarcce.com 1606

 ISSN (Print) : 2319-5940
ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 3, March 2013

Histogram specification technique is another approach for contrast

enhancement. In this method, the shape of the histogram is specified
manually and then a transformation function is constructed based in
this histogram input image at gray levels. Image histogram is
partitioned based on local minima and specific gray level ranges that
are assigned to each partition. After partitioning, HE is applied on
each partition. To more clearly show contrast enhancement of HE
based we attempt a brief review of existing systems of contrast
enhancement methods. Table 1 show a brief survey of HE – based.
Fig 4. γth power and γth root curves for c=1. Tone Mapping is another approach of contrast enhancement
techniques. In this method if we want to output high dynamic range
Piecewise-linear transformation function is an arbitrary user defined (HDR) image on paper or on a display. We must somehow convert
transformation as shown in Fig 8. Based on setting of (r1, s1) and (r2, the wide intensity range in the image to the lower range supported by
s2) different types linear transformations can be achieved. the display. This technique used in image processing and computer
graphics to map a set of colours to another, often approximate the
appearance of high dynamic range images in media with a more
limited dynamic range. Tone mapping is done in the luminance
channel only and in logarithmic scale. It is used to convert floating
point radiance map into 8-bit representation for rendering
applications. The two main aims of tone mapping algorithm:
Fig. 5 Original image and its stretched image Preserving image details and providing enough absolute brightness
There are three types of Piecewise linear transformations: Contrast information in low dynamic range tone mapped image. Intensity
Stretching, Intensity level slicing and Bit plane slicing. Contrast Level or Gray level Slicing is another technique of Piecewise linear
Stretching is one of image enhancement techniques involves transformation in which gray or Intensity level slicing high lights
processing an image to make it look better to human viewers. It is certain range of gray levels in the original image. These
usually used for post processing by modifying contrast or dynamic transformations permit segmentation of certain gray level regions
range or both in an image. The aim of contrast enhancement process from the rest of the image. This technique is useful when different
is to adjust the local contrast in different regions of the image so that features of an image are contained in different gray levels. Bit plane
the details in dark or bright regions are brought out and revealed to Slicing is another form of Piecewise transformation which highlights
the human viewers. Contract enhancement is usually applied to input the contribution made to total image appearance by specific bits used
images to obtain a superior visual representation of the image by for pixel gray levels and determines the adequacy of number of bits
transforming original pixel values using a transform function of the used to quantize each pixel in image compression. spatial Filter
form as g(x, y)=T[r(x, y)] where g(x, y) and r(x, y) are the output and Operations are performed on a pixel along with its immediate
the input pixel values at image position. This process improves the neighbours; this is also called as neighbourhood operations. Based on
contrast by stretching the range of gray level values to span a desired type of operations performed on the pixels spatial filters are classified
range of gray level values. This transformation is also called as image into two categories: Linear and Nonlinear spatial filters. Linear spatial
intensity transformation or normalization. Let a, b be the minimum filter process involves convolving a mask with an image i.e. passing a
and maximum pixel values of f(x, y) and c, d be the minimum and weighted mask over the entire image. Mask is also referred as
maximum pixel values of g(x, y). Normalization can be achieved by window, template, or kernel. Non linear spatial filter are those filters
scaling each pixel in original image value as s=(r-c) (b-a)/ (d-c) + a. in which enhanced image is not linearly related to pixels in the
The existing techniques of contrast enhancement techniques can be neighbourhood of original image. Max filter is used to locate the
again sub divided into two groups: direct and indirect methods. Direct brightest point in an image. It is a 100th percentile filter and removes
methods define a contrast measure and try to improve it. Indirect salt noise whereas Min filter is used to locate the darkest point in an
methods on the other hand, improve the contrast through exploiting image. It is a 0th percentile filter and removes pepper noise and
the underutilized regions or the dynamic range without defining a Median filter is a statistical filter used to locate the median value of
specific contrast term. In this paper contrast enhancement techniques the pixels. It removes salt and pepper noise. This filter provides less
can be broadly categorized into groups: Histogram Equalization (HE), blur but rounds corners.
Tone Mapping. Histogram Equalization is one of the most commonly
used methods for contrast enhancement. It attempts to alter the spatial IV. FREQUENCY DOMAIN TECHNIQUES
histogram of an image to closely match a uniform distribution. The
main objective of this method is to achieve a uniform distributed Frequency domain techniques are based on the manipulation of the
histogram by using the cumulative density function of the input orthogonal transform of the image rather than the image itself.
image. The advantages of the HE include it suffers from the problem Frequency domain techniques are suited for processing the image
of being poorly suited for retaining local detail due to its global according to the frequency content. The principle behind the
treatment of the image small- scale details that are often associated frequency domain methods of image enhancement consists of
with the small bins of the histogram are eliminated. The disadvantage computing a 2-D discrete unitary transform of the image, for instance
is that it is not a suitable property in some applications such as the 2-D DFT, manipulating the transform coefficients by an operator
consumer electronic products, where brightness preservation is M, and then performing the inverse transform. The orthogonal
necessary to avoid annoying artifacts. The equalization result is transform of the image has two components magnitude and phase.
usually an undesired loss of visual data of quality and of intensity The magnitude consists of the frequency content of the image. The
scale. phase is used to restore the image back to the spatial domain. The

Copyright to IJARCCE www.ijarcce.com 1607

 ISSN (Print) : 2319-5940
ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 3, March 2013

Author Year Operating Domain Model Processing techniques Application

Agaian SS[7] 2007 Spatial domain HE based Logarithmic Log reduction zonal magnitude Traffic monitoring; Security
transform LTHS technique; Logarithmic transform Surveillance
histogram shifting
Hao Hu[8] 2010 Spatial domain Content adaptive video Content classification and adaptive Computer vision
processing model processing
Tarik Arici[9] 2009 Spatial domain HE based modification Histogram modification LCD display device; Low
framework, content adaptive quality video
algorithm
Sangkeun Lee[10] 2007 Spatial domain Dynamic range compression Discrete Cosine transform(DCT); Image/video compressing
Retinex theory
Viet Anhnguyen[11] 2009 Spatial domain Cauchy distribution model; Video reconstructed from multiple Compression video
Transform domain AC transform coefficient compressed copies of video content
R.C. Gonzalez[12] 2008 Spatial domain HE Global Histogram Equalization Image/ Video Security
Surveillance
Xuan Dong[13] 2010 Spatial domain Image Inverting Model Inverting the input low lighting Traffic monitoring; Medical
video; dehaze algorithm imaging
Shan Du[14] 2010 Spatial domain ARHE model Adaptive Region based Method Face Recognition
A.A Wadud M[15] 2007 Spatial domain Dynamic Histogram Dynamic Histogram Equalization Medical Image, Low quality
equalization technique video
Boudraa A.O[16] 2008 Spatial domain 2DTKEO model 2D Teager- Kaiser Energy Medical image; Satellite
Operator image
David Menotti[17] 2007 Spatial domain MHE model Multi histogram equalization Image processing
methods
Sara Hashem[18] 2010 Spatial domain Improve HE Genetic algorithms Compute high dynamic range
image processing
George D[19] 2009 Spatial domain Improve HS and HE Histogram based image Image processing
enhancement
Table 1. A Brief Survey of Histogram Enhancement Techniques

usual orthogonal transforms are discrete cosine transform, discrete imaging, Medical imaging, Digital camera application, Remote
Fourier transform, Hartley Transform etc. The transform domain sensing, Image Enhancement techniques used in many areas such as
enables operation on the frequency content of the image, and forensics, Astrophotography, Fingerprint matching, etc. The better
therefore high frequency content such as edges and other subtle result for Image enhancement has also used in real time enhancement
information can easily be enhanced. Frequency domain which of neuro evolution of augmenting. IE techniques when applied to
operate on the Fourier transform of an image. pictures and videos help the visually impaired in reading small print,
 Edges and sharp transitions (e.g. noise) in an image contribute using computers and television, and face recognition. Color contrast
significantly to high frequency content of Fourier transform. enhancement, sharpening and brightening are just some of the
 Low frequency contents in the Fourier transform are responsible techniques used to make the images vivid. In the field of e-learning,
to the general appearance of the image over smooth areas. IE is used to clarify the contents of chalkboard as viewed on streamed
The concept of filtering is easier to visualize in the frequency domain. video; it improves the content readability. Medical imaging uses this
Therefore, enhancement of image f(x, y) can be done in the for reducing noise and sharpening details to improve the visual
frequency domain based on DFT. This is particularly useful in representation of the image. This makes IE a necessary aiding tool
convolution if the spatial extent of the point spread sequence h(x, y) is for reviewing anatomic areas in MRI, ultrasound and x-rays to name a
large then convolution theory. few. In forensics IE is used for identification, evidence gathering and
g(x, y)= h(x, y) f(x, y) surveillance. Images obtained from fingerprint detection, security
where g(x, y) is enhanced image. videos analysis and crime scene investigations are enhanced to help in
identification of culprits and protection of victims.
Fourier Filter Inverse Fourier VI. OBSERVATIONS
Transform Function Transform The point processing methods are most primitive, yet essential image
processing operations and are used primarily for contrast
enhancement. Image Negative is suited for enhancing white detail
embedded in dark regions and has applications in medical imaging.
Preprocessing Post Processing Power-law transformations are useful for general purpose contrast
manipulation. For a dark image, an expansion of gray levels is
accomplished using a power-law transformation with a fractional
exponent. Log Transformation is useful for enhancing details in the
f(x, y) g(x, y) darker regions of the image at the expense of detail in the brighter
Input Image Enhance Image regions the higher-level values. For an image having a washed-out
appearance, a compression of gray levels is obtained using a power-
law transformation with γ greater than 1. The histogram of an image
(i.e., a plot of the gray level frequencies) provides important
V. APPLICATIONS information regarding the contrast of an image. Histogram
equalization is a transformation that stretches the contrast by
Image enhancement is used for enhancing a quality of images. The redistributing the gray-level values uniformly.
applications of image enhancement are Aerial imaging, Satellite
Copyright to IJARCCE www.ijarcce.com 1608
 ISSN (Print) : 2319-5940
ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 3, March 2013

VII. CONCLUSION [11] V. A. Nguyen, Y. P. Tan and Z. H. Chen, “On the method of multicopy
video enhancement in transform domain”, Proc. of the 16th IEEE
Image enhancement algorithms offer a wide variety of approaches International Conference on Image Processing, pp. 2777- 2780, 2009
[12] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice
for modifying images to achieve visually acceptable images. The
Hall, New Jersey, 2008.
choice of such techniques is a function of the specific task, image [13] X. Dong, Y. Pang and J.Wen, “Fast efficient algorithm for
content, observer characteristics, and viewing conditions. The review enhancement of low lighting video”, Proc. Of the 37th International
of Image enhancement techniques in Spatial domain have been Conference and Exhibition on Computer Graphics and Interactive
successfully accomplished and is one of the most important and Techniques,2010.
difficult component of digital image processing and the results for [14] A. A. Wadud, M. Kabir, M. H. Dewan and M. C. Oksam, “A dynamic
each method are also discussed. Based on the type of image and type histogram equalization for image contrast enhancement”, IEEE Trans.
of noise with which it is corrupted, a slight change in individual Consumer Electronic, vol. 53, no. 2, pp. 593-600, 2007.
[15] S. S. Agaian, S. Blair and K. A. Panetta, “Transform coefficient
method or combination of any methods further improves visual
histogram-based image enhancement algorithms using contrast
quality. In this survey, we focus on survey the existing techniques of entropy”, IEEE Trans. Image Processing, vol. 16, no. 3, pp. 741-758,
image enhancement, which can be classified into two broad categories 2007.
as spatial domain enhancement and Frequency domain based [16] A. O. Boudraa and E. H. S. Diop, “Image contrast enhancement based
enhancement. We show the existing technique of image enhancement on 2D teager-kaiser operator”, Proc. of the IEEE International
and discuss the advantages and disadvantages of these algorithms. Conference on Image Processing , pp. 3180-3183, 2008.
Although we did not discuss the computational cost of enhancement [17] S. Hashemi, S. Kiani, N. Noroozi and M. E. Moghaddam, “An image
algorithms it may play a critical role in choosing an algorithm for contrast enhancement method based on genetic algorithm”, Pattern
Recognition Letters, vol. 31, no. 13, pp. 1816-1824, 2010.
real-time applications. We also have described recent developments
[18] D. G. Toderici and J. Yagnik, “Automatic, efficient, temporally-
methods of image enhancement and point out promising directions on coherent video enhancement for large scale applications”, Proc. of the 17th
research for image enhancement in spatial domain for future research. ACM International Conference on Multimedia, pp. 609-612, 2009.
The future scope will be the development of adaptive algorithms for [19] I. Jafar and H. Ying, A new method for image contrast enhancement
effective image enhancement using Fuzzy Logic and Neural Network. based on automatic specification of local histograms, International Journal of
Computer Science and Network Security , vol. 7, no. 7, pp. 1-10, 2007
REFERENCES
0
[1] Arun R, Madhu S. Nair, R. Vrinthavani and Rao Tatavarti. “An Alpha
Rooting Based Hybrid Technique for Image Enhancement”. Online
Dr. S. S. Bedi is an active researcher in the field of Image
publication in IAENG, 24th August 2011.
[2] Agaian, SOS S., Blair Silver, Karen A. Panetta, “Transform Coefficient processing. Currently working as Assistant Professor in the
Histogram-Based Image Enhancement Algorithms Using Contrast Department of Computer Sciene at MJP
Entropy”, IEEE Transaction on Image Processing, Vol. 16, No. 3, March Rohilkhand University, Bareilly (U.P.), India.
2007
He has done his Ph.D from IIIT, Gwalior
[3] Jinshan Tang Eli Peli, and Scott Acton, “Image Enhancement Using a
Contrast Measure in the Compressed Domain”, IEEE Signal processing (M.P.) and M.Tech from Thapar University,
Letters , Vol. 10, NO. 10, October 2003 Punjab. He has published many papers in
[4] R. Mantiuk, S. Daly and L. Kerofsky, “Display adaptive tone mapping”, International Conferences and Journals.
ACM Trans. Graphics, vol.27, no. 3, pp. 681-690, 2008.
[5] R. P. Kovaleski and M. M. Oliveira, “High-quality brightness enhancement
functions for real-time reverse tone mapping”, Visual Computer, vol. 25,
no. 5, pp. 539-547, 2009.
[6] T. Jinno, M. Okuda and N. Adami, “Acquisition and encoding of high Rati Khandelwal received MCA degree
dynamic range images using inverse tone mapping”, Proc. of IEEE from MJP Rohilkhand
International Conference on Image Processing, vol. 4, pp.181-184, 2007.
University, Bareilly (U.P.) in 2006. Currently
[7] S. S. Agaian, S. Blair and K. A. Panetta, “Transform coefficient
histogram-based image enhancement algorithms using contrast entropy”, she is pursuing M.Tech degree in Computer
IEEE Trans. Image Processing, vol. 16, no. 3, pp. 741-758, 2007. Science from Banasthali University, Jaipur
[8] H. Hu, “Video enhancement: content classification and model selection”, (Rajasthan.) Her research interest includes
Ph. D. Thesis, Technique Universities Eindhoven, Eindhoven,
Image Processing .She has published many
Netherlands, 2010.
[9] YunBo Rao and Leiting Chen, “An efficient contourlet transform-based papers in International Journals.
algorithm for video enhancement”, Journal of Information Hiding and
Multimedia Signal Processing, vol. 2, no. 3, pp. 282-293, 2011.
[10] S. Lee, “An efficient content-based image enhancement in the
compressed domain using Retinex theory”, IEEE Trans. Circuits and
Systems for Video Technology, vol. 17, no. 2, pp. 199-213, 2007.

Copyright to IJARCCE www.ijarcce.com 1609