HITEC University

Department of Electrical Engineering

Digital Image Enhancement

Supervised By:
Group Members:
Dr. Jameel Ahmed
Nisar Ahmed Rana
Engr. Waqas Ahmed
Sheikh M. Arshad
Ghazal Arshad
Maria Minhas
Digital Image Enhancement

Introduction to Image Processing and Enhancement

Image processing modifies pictures to improve them (enhancement, restoration), extract information
and change their structure. Images can be processed by optical, photographic, and electronic means,
but image processing using digital computers is the most common method because digital methods
are fast, flexible, and precise.

In computer graphics, the process of improving the quality of a digitally stored image by manipulating
the image with software is called image enhancement. It is quite easy, for example, to make an image
lighter or darker, or to increase or decrease contrast. Advanced image enhancement software also
supports many filters for altering images in various ways.

An image can be synthesized from a micrograph of various cell organelles by assigning a light
intensity value to each cell organelle. The sensor signal is “digitized”-- converted to an array of
numerical values, each value representing the light intensity of a small area of the cell. The digitized
values are called picture elements, or “pixels,” and are stored in computer memory as a digital image.
A typical size for a digital image is an array of 512 by 512 pixels, where each pixel has value in the
range of 0 to 255. The digital image is processed by a computer to achieve the desired result.

Image enhancement improves the quality (clarity) of images for human viewing. Removing blurring
and noise, increasing contrast, and revealing details are examples of enhancement operations. For
example, an image might be taken of an endothelial cell, which might be of low contrast and
somewhat blurred. Reducing the noise and blurring and increasing the contrast range could enhance
the image. The original image might have areas of very high and very low intensity, which mask
details. An adaptive enhancement algorithm reveals these details. Adaptive algorithms adjust their
operation based on the image information (pixels) being processed. In this case the mean intensity,
contrast, and sharpness (amount of blur removal) could be adjusted based on the pixel intensity
statistics in various areas of the image.

Image enhancement refers to sharpening of image features such as edges, boundaries, or contrast to
make a graphic display more useful for display and analysis. The enhancement process does not
increase the inherent information content in the data. But it does increase the dynamic range of the
chosen features so that they can be detected easily. Image enhancement includes gray level and
contrast manipulation, noise reduction, edge sharpening and so on. Image processing is useful in
virtually all image processing applications.

Image processing technology is used by planetary scientists to enhance images of Mars, Venus, or
other planets. Doctors use this technology to manipulate CAT scans and MRI images. Image
processing in the laboratory can motivate students and make science relevant to student learning.
Image processing is an excellent topic for classroom application of science research techniques.

Major Image Enhancement Features

 Brightness/Contrast  Softening
 Color Correction  Photo Filter
 Gamma Correction  Image Filtering
 De-Noising  Edge Enhancement
 De-Blurring  Auto Adjust
 Sharpening  Special Effects

1
Digital Image Enhancement

PROJECT DESCRIPTION
 Image Acquisition
 Image enhancement
 Image restoration
 Graphical user interface

IMAGE ENHANCEMENT

The aim of image enhancement is to improve the interpretability or perception of information in

images for human viewers, or to provide `better' input for other automated image processing
techniques.

Image enhancement techniques can be divided into two broad categories:

1. Spatial domain methods, which operate directly on pixels.

2. Frequency domain methods, which operate on the Fourier transform of an image.

Histogram Modeling

The histogram of an image represents the relative frequency occurrence of the various gray levels
in the image. Histogram modeling modifies an image so that its histogram has a desired shape.
This is useful in stretching the low-contrast level of images with narrow histograms. Histogram
modeling is found to be a powerful technique for image enhancement.

 Histogram Equalization

Histeq() enhances the contrast of images by transforming the values in an intensity image, so
that the histogram of the output image approximately matches a specified histogram.

 Adaptive Histogram Equalization

adapthisteq() enhances the contrast of the grayscale image I by transforming the values using
contrast-limited adaptive histogram equalization (CLAHE).CLAHE operates on small regions
in the image, called tiles, rather than the entire image. Each tile's contrast is enhanced, so
that the histogram of the output region approximately matches the histogram specified by the
'Distribution' parameter. The neighboring tiles are then combined using bilinear interpolation
to eliminate artificially induced boundaries.

Contrast Enhancement

 Intensity adjustment
To increase the contrast of the image, we need to adjust the intensity of an image.Using
imadjust() the contrast is enhanced.
 ir=I(:,:,1); ig=I(:,:,2); ib=I(:,:,3);
 ir=imadjust(ir); ig=imadjust(ig); ib=imadjust(ib);
 img(:,:,1)=ir; img(:,:,2)=ig; img(:,:,3)=ib;
img is the output image with better contrast.

1
Digital Image Enhancement

 Brightness

The brightness of the input image is increased to the desired level by taking the value from
the user and increasing the intensity of input image to that level.

 bright=str2num(b);
 img=I+bright;
 imshow(img);

IMAGE RESTORATION
The purpose of image restoration is to "compensate for" or "undo" defects which degrade an image.
Degradation comes in many forms such as motion blur, noise, and camera miss-focus. In cases like
motion blur, it is possible to come up with an very good estimate of the actual blurring function and
"undo" the blur to restore the original image. In cases where the image is corrupted by noise, the best
we may hope to do is to compensate for the degradation it caused.

Deblur

 Weiner Filtering
Image restoration using wiener filtering provides us with the optimal trade-off between de-
noising and inverse filtering.
 Weiner Filtering is implemented in IPT using function deconvwnr
 J = deconvwnr (I, PSF) restores image I that was degraded by convolution with a
point-spread function PSF and possibly by additive noise.
 PSF is obtained using fspecial() which creates a two dimensional filter of specified
type and parameters. Parameters will be defined by the user of his own requirment,
using the Edit Text Box in the user friendly GUI. It is implemented using:
 psf=fspecial('motion',len,theta);
 img=deconvwnr(I,psf);
 Blind Deconvolution
In this method, we assume nothing about the image. We do not have any information about
the blurring function or on the additive noise. The most difficult problems in image restoration
are obtaining a suitable estimate of the PSF to use in restoration algorithms.
 Image restoration methods that are not based on specific knowledge of the
PSF are called blind deconvolution algorithms. Blind deconvolution is
implemented in IPT using function deconvblind
 [J,PSF] = deconvblind (I, INITPSF) deconvolves image I using the maximum
likelihood algorithm, returning both the deblurred image J and a restored
point-spread function PSF.
 Inverse Filter
In this method we look at an image assuming a known blurring function. Restoration is good
when noise is not present and not so good when it is present.

Denoise

 Removing Noise By Median Filtering

Median filtering is similar to using an averaging filter, in that each output pixel is set to an
average of the pixel values in the neighborhood of the corresponding input pixel. However,
with median filtering, the value of an output pixel is determined by the median of the

2
Digital Image Enhancement

neighborhood pixels, rather than the mean. The median is much less sensitive than the mean
to extreme values (called outliers). Median filtering is therefore better able to remove these
outliers without reducing the sharpness of the image. The medfilt2 function implements
median filtering.

 Removing Noise By Adaptive Filtering

The wiener2 function applies a Wiener filter (a type of linear filter) to an image adaptively,
tailoring itself to the local image variance. Where the variance is large, wiener2 performs little
smoothing. Where the variance is small, wiener2 performs more smoothing. This approach
often produces better results than linear filtering. The adaptive filter is more selective than a
comparable linear filter, preserving edges and other high-frequency parts of an image. In
addition, there are no design tasks; the wiener2 function handles all preliminary computations
and implements the filter for an input image. wiener2, however, does require more
computation time than linear filtering. wiener2 works best when the noise is constant-power
("white") additive noise, such as Gaussian noise.

GRAPHICAL USER INTERFACE

The Graphical User Interface (GUI) of our project is completed. And the coding part is in progress.
Using different GUI components, the GUI model is made user friendly. Following is the Graphical User
Interface which is designed in a way that a person who does not know about image processing, is
even able to enhance the feature of his image. Features can be enhanced automatically or manually.

3
Digital Image Enhancement

Graphical User Interface Components:

GUI is made using push buttons, sliders, axes, menu items etc

 Push Button: Several functions are performed using a push buttion. Clicking on the push
button, performs the operation specified.

 Axes: Axes components enable our GUI to display graphics, such as graphs and images.

 Slider: Sliders accept numeric input within a specified range by enabling the user to move a
sliding bar, which is called a slider or thumb. Users move the slider by clicking the slider and
dragging it, by clicking in the trough, or by clicking an arrow. The location of the slider
indicates the relative location within the specified range.

 Edit Box: Edit text components are fields that enable to enter or modify text strings. Edit
text are used where we want text as input. Users can enter numbers, and it is converted to
their numeric equivalents using str2num().

4
Digital Image Enhancement

 Menu Title: Because clicking a menu title automatically displays the menu below it, we dnt
need to program callbacks at the title level. However, the callback associated with a menu
title can be a good place to enable or disable menu items below it.

Programming of Graphical User Interface

 Load Function:

function load_Callback(hObject, eventdata, handles)

[FileName,PName] = uigetfile('*.jpeg;*.jpg','Select JPEG Image');
i=strcat(PName,FileName);
global I;
global img;
I=imread(i);
img=I;
axes(handles.axes);
imshow(img);

 Image Resize:
function Resize_Callback(hObject, eventdata, handles)
global I;
global img;
str=get(handles.re,'String');
scale=str2num(str);
scale=scale/100;
img=imresize(I,scale);
axes(handles.axes);
imshow(img);

 Image Rotate:
function Rotate_Callback(hObject, eventdata, handles)
global I;
global img;
str=get(handles.ro,'String');
theta=str2num(str);
img=imrotate(I,theta);
axes(handles.axes);
imshow(img);

 Image Crop:
function Crop_Callback(hObject, eventdata, handles)
global I;
global img;
str=get(handles.hi,'String'); str=get(handles.vf,'String');
hi=str2num(str); vf=str2num(str);
str=get(handles.hf,'String'); img=I(50:305,60:315,:);
hf=str2num(str); axes(handles.axes);
str=get(handles.vi,'String'); imshow(img);
vi=str2num(str);

5
MANAGEMENT SUMMARY

The project design team consisted of 4 members from Electrical Engineering Department. The team
was split into a number of technical groups with a designated leader for each. The team leader was
responsible for running meetings, procurement and other administrative tasks. Each member of the
design team belonged to at least one technical group.

Role Name Project Development Responsibility

Project Planner Nisar Ahmed Rana Prepares and administers project plans. Tracks
and reports progress.
Programmer Maria Minhas & Assists the Designer in writing programs.
Ghazal Arshad
Independent Tester Sheikh Arshad & Conducts testing of the application at all stages
Maria Minhas of development.
Documentation Ghazal Arshad & Writes the user and programmer manuals.
Specialist Sheikh Arshad
Project Designer Nisar Ahmed Rana Produces the Design Specification and program
an application, based on the Requirements. The
Designer is responsible for delegating program
assignments to the Programmer
Analyst Nisar Ahmed Rana Debugs the software and implements it.

TECHNICAL GROUPS

Each technical group was assigned a leader who was responsible for getting the group to meet the
deadlines set forth by the GL and the rest of the team.
Project Planning
Technical Group

Implementation
Documentation

User Manual

GUI Design
Debugging

Testing
Coding

Member Name
Nisar Ahmed Rana 1 2 2 1 1 3 2 1
Sheikh Arshad 2 2 2 2 3 1 1 2
Ghazal Arshad 2 1 2 3 3 2 3 2
Maria Minhas 2 3 1 2 3 3 2 3

The Project Planning group is incharge of all the groups in designing and idea generation. Testing
group is responsible for testing the performance of the software and save the results. The
implementation group designs the software and delegate the program assignment to the
programmers. The debugging group debugs the errors if reported by testing group. Coding group
assist the programmer in writing codes and studying algorithms. GUI design group assist the designer
in designing and modification of Graphical User Interface of application. The Documentation group
Digital Image Enhancement

was responsible for documenting the design and writing the report. User manual group write the user
manual with the help of Documentation and Coding group.

TIME SCHEDULING
The first task for the team was to set an aggressive, yet achievable schedule. To ensure the
successful completion of the project, the task as a whole has been broken up into various sub-tasks.
These sub-tasks were chosen after evaluating the problem and finding crucial steps that could be
followed to completion. In order to meet the aggressive schedule, two team meetings were held each
nd
week one under the co-supervisor and the 2 under group leader throughout the project. The group
has to report its performance to its supervisor after every 15 days. In addition, each technical group
met at least once a week when it had an approaching deadline. The deadlines that have been chosen
will be adhered to unless requested otherwise by the Supervisor.

Gantt Chart
In the Gantt chart shown, tasks illustrated in blue are completed. Areas in green depict the tasks that
our team will be focusing on during the specified given period. It should be noted, that the direct
development and testing of code is placed on this chart. This is an ongoing process comprising the
latter part of the project. Key areas that will involve a significant amount of time to prepare include the
user manual.