Chapter Three

Image Enhancement
• Digital image processing involves the manipulation
and interpretation of digital images with the aid of
a computer.
• the common image processing functions available
in image analysis systems can be categorized into
the following four categories:
– Preprocessing
– Image Enhancement
– Image Transformation
– Image Classification and Analysis
• Preprocessing functions: operations required prior to the
main data analysis and extraction of information to correct
image data for distortion or degradation that stem from the
image acquisition process.

• Pre-processing operations, sometimes referred to as image

restoration and rectification
• Pre-processing involves
– Geometric correction :the initial processing of raw image data to
correct for geometric distortions (to bring an image into registration with
a map or another image),
– Radiometric Correction: to calibrate the data radiometrically (to adjust
digital values for the effect of a hazy atmosphere)
– Noise Removal: to eliminate noise present in the data.
 Image enhancement
The aim of digital enhancement is to amplify
these slight differences for better clarity of the
image scene. This means digital enhancement
increases the separability (contrast) between
the interested classes or features.

The digital image enhancement may be

defined as some mathematical operation that
are to be applied to digital remote sensing
input data to improve the visual appearance
of an image for better interpretability or
subsequent digital analysis.
 Continue……………..
• To improve the visual interpretability of an
image by increasing the apparent/noticeable
distinction between the features of the scene.
• This objective is to create new image from the
original image in order to increase the amount
of information that can be visually interpreted
from the data.
• Enhancement operations are normally applied
to image data after the appropriate restoration
procedures have been performed.
The common problems that can be remove by
image enhancement-

• Low sensitivity of detectors,

• Weak signal of objects present on earth
surface,
• Similar reflection of different objects,
• Environment condition at the time of
recording, and
• Human eye is poor at discriminating the
differences.
 Image Enhancement Techniques

The term enhancement is used to mean the alteration

of the appearance of an image in such a way that the
information contained in that image is more readily
interpreted visually in terms of a particular need.

The image enhancement techniques are applied either

to single-band images or separately to the individual
bands of a multiband image set. These techniques can
be categorized into two:

1. Spectral Enhancement Techniques

2. Multi-Spectral Enhancement Techniques
Density Slicing

•Density Slicing is the mapping of a range of

contiguous grey levels of a single band image and
in the multi spectral image

•The DNs of a given band are "sliced" into distinct

classes. For example, for band 4 of a TM, we
might divide the 0-255 continuous range into
discrete intervals of 0-63, 64-127, 128-191 and
192-255.
Contrast Stretching

• Contrast refers to the range of values present on an

image
•The full dynamic range of sensor will be used and
the corresponding image is dull and lacking in
contrast or over bright.

• The result is an image lacking in contrast - but by

remapping the DN distribution to the full display
capabilities of an image processing system, we can
recover a beautiful image.
Contrast Stretching can be displayed in two
categories:
1. Linear Contrast Stretching
2. Histogram Equalization
 Contrast Tools
255
10 Bins
2 SD • Histogram Equalization
Tries to put equal numbers of pixels in a set
Frequency

of bins.

• Linear Stretch
Linear stretch between a lower and a upper
value
0 255
 Image Contrast
• Dark

Frequency
• Little CONTRAST
between features

0 255

• Brighter

Frequency
• More CONTRAST between
features

0 255
Image Contrast

Pixel Values of raw

image
Values as they could
appear in display

Frequency

0 255
Dark Bright
 Stretching Image Histograms
• Fits the narrow range

Frequency
of raw data… IMAGE
…into the larger range of the
display device 0 255

Achieved using a Look

Up Table (LUT)

Frequency
SCREEN

0 255
 Contrast Stretch
• Stretches the range of data from the lower
values to the higher values so there is higher
contrast when an image is displayed
Frequency

s s m ms s
0 255
Histogram Equalization (or uniform
distribution stretch): Input pixels are
redistributed to produce a uniform population
density of pixels along the output axis,

which results in the output histogram having a

wide spacing of bins (all pixels having the
same DN) in the center of the distribution
curve and a close spacing of the less-
populated bins at the head and tail of the
histogram.
 Cont…

• A histogram is a graphical representation of the

brightness values that comprise an image. The
brightness values (i.e. 0-255) are displayed along
the x axis of the graph. The frequency of
occurrence of each of these values in the image is
shown on the y-axis.

• By manipulating the range of digital values in an

image, graphically represented by its histogram,
we can apply various enhancements to the data.
 Contrast Stretching
• To expand the narrow range of brightness values of an
input image over a wider range of gray values

• Certain features may reflect more energy than others. This

results in good contrast within the image and features that
are easy to distinguish

• The contrast level between the features in an image is low

when features reflect nearly the same level of energy

• When image data are acquired, the detected energy does

not necessarily fill the entire grey level range that the
sensor is capable of. This can result in a large
concentration of values in a small region of grey levels
producing an image with very little contrast among the
features.
Contrast Stretching
 Contrast Stretching
• Linear stretch:

DN' ( MAX
DN MIN
MIN
)255
Where
DN’= Digital no. assigned to pixel in output image
DN= Original DN of pixel in input image
Minimum value of input image (0)
MIN=
MAX=Maximum value of input image (255)
Linear stretch
Non-linear
 Spatial filtering

• Spatial filtering is a window-based image processing

technique for altering the input pixel value based on its
own value and the value of the pixels surrounding it.
• Encompasses another set of digital processing
functions which are used to enhance the
appearance of an image. Spatial filters are
designed to highlight or suppress specific features
in an image based on their spatial frequency.
 Neighborhood and Connectivity
 Kernels and Convolution
 Spatial Feature Manipulation
• Spatial filters pass (emphasize) or suppress (de-emphasize) image data of
various spatial frequencies
• Spatial frequency refers to the number of changes in brightness value for
any area within a scene

• High spatial frequency  rough areas

– High frequency corresponds to image elements of smallest size
– An area with high spatial frequency will have rapid change in digital
values with distance (i.e. dense urban areas and street networks)
• Low spatial frequency  smooth areas
– Low frequency corresponds to image elements of (relatively) large
size.
– An object with a low spatial frequency only changes slightly over
many pixels and will have gradual transitions in digital values (i.e. a
lake or a smooth water surface).
 The Neighbourhood
• A re-sampling technique that calculates the
brightness value of a pixel in a corrected image from
the brightness value of the pixel nearest the location
of the pixel in the input image

Around a target pixel (A)

B: Kernel or neighborhood
 Numerical Filters-Low Pass Filters

• A low-pass filter is designed to

emphasize larger, homogeneous
areas of similar tone and reduce 1 1 1
the smaller detail in an image. 1 1 1

• Thus, low-pass filters generally 1 1 1

serve to smooth the appearance
of an image. Average and median
of 3x3 pixels.
Low-pass Filters
 Low-pass Filters

Details are “smoothed”

and DNs are averaged after
a low pass filter is applied
to an image.
 High-pass Filter
High-pass filters do the opposite and serve to
sharpen the appearance of fine detail in an
image.
One implementation of a high-pass filter first
applies a low-pass filter to an image and then
subtracts the result from the
original, leaving behind only
the high spatial frequency information.

Streets and highways, and some

streams and ridges, are greatly
emphasized. The trademark of a
high pass filter image is that linear
features commonly are defined as
bright lines with a dark border.
High-pass Filter
 Edge Enhancement

• Edge-enhanced images attempt to preserve local

contrast and low-frequency brightness
information, for example related to linear
features such as roads, canals, geological faults,
etc.
 Edge Enhancement
• Edge enhancement is typically implemented in three
steps:

– High-frequency component image is produced using

the appropriate kernel size. Rough images suggest
small filter size (e.g. 3 × 3 pixels) whereas large
sizes (e.g. 9 × 9) are used with smooth images.

– All or a fraction of the gray level in each pixel is

added back to high-frequency component image

– The composite image is contrast-stretched

 Band Rationing
• Band Rationing or Division of images is probably
the most common arithmetic operation that is
most widely applied to images in geological,
ecological and agricultural applications of
remote sensing.

• Ratio Images are enhancements resulting from

the division of DN values of one spectral band
by corresponding DN of another band.
 Fourier Analysis
• Fourier analysis used to convert a raster image
(normal) from the spatial domain into a
frequency domain image.
• Analyst can edit the Fourier image to reduce
noise or remove striping and lines.
• Once the Fourier image is edited, it is then
transformed back into the spatial domain by
using an inverse Fourier analysis. The result is an
corrected version of the original image.
 Fourier Transformation
• Fourier transform operates on a single band
image, not on a multispectral data set.
• For that, first we have to identify in which band
the striping's are coming.
• After identification of striping we have to
transform and remove the error through
transform editor tool.
 Fourier Analysis

Noise Error Image Corrected Image

 Normalized Difference Vegetation Index (NDVI)

• Ratio images are often useful for discriminating

fine differences in spectral variations, in a scene
that is masked by brightness variations.
• The utility of any given spectral ratio depends
upon the particular reflectance characteristics
of the features involved and the application at
hand.
• For example a near-infrared / red ratio image
might be useful for differentiating between
areas of stressed and non-stressed vegetation.
Continue………….
• Various mathematical combinations of satellite
bands, have been found to be sensitive indicators
of the presence and condition of green
vegetation.
• These band combinations are thus referred to as
vegetation indices. Two such indices are the
simple Vegetation Index (VI) and the Normalized
Difference Vegetation Index (NDVI).
• Both are based on the reflectance properties of
vegetated areas as compared to clouds, water
and snow on the one hand, and rocks and bare
soil on the other.
Continue…….

• Vegetated areas have a relatively high

reflection in the near-infrared and a low
reflection in the visible range of the spectrum.
• NDVI shows the vegetation health according
to the presence of chlorophyll content in the
leaves.

NDVI = Band 4 (NIR) – Band 3 (IR) /

Band 4 (NIR) + Band 3 (IR)