ATTENTION GATE ResU-Net FOR

AUTOMATIC BRAIN TUMOR

SEGMENTATION

A PROJECT REPORT
submitted by

SARANYA.G (721917106073)
SARGADILEEPKUMAR.T.N (721917106074)
SWAPNA.P (721917106088)
YUVASREE.A (721917106097)

In partial fulfilment for the award of the degree

of

BACHELOR OF ENGINEERING
IN

ELECTRONICS AND COMMUNICATION ENGINEERING

DHANALAKASHMI SRINIVASAN COLLEGE OF ENGINEERING

COIMBATORE-641105

ANNAUNIVERSITY:CHENNAI 600 025

APRIL2021
CERTIFICATE
 ANNAUNIVERSITY : CHENNAI 600 025

BONAFIDE CERTIFICATE

It is certified that this project report “ ATTENTION GATE ResU-Net FOR

AUTOMATIC BRAIN TUMOR SEGMENTATION” is the bonafide work of
“SARANYA.G(721917106073) , SARGA DILEEPKUMAR.T.N(721917106074),
SWAPNA.P(721917106088), YUVASREE.A(721917106097)” who carried out the
project work under my supervision.

SIGNATURE SIGNATURE
SUPERVISOR HEAD OFTHE DEPARTMENT
Mrs.S.G.RAMAPRIYANGA,M.E Mr.S.MUKUNTHAN M.TECH
Assistant Professor Assistant Professor,Head of the
Department of Electronics Department
and communication Department of Electronics and
Engineering Communication Engineering
Dhanalakshmi Srinivasan College Dhanalakshmi Srinivasan College
of Engineering of Engineering
Coimbatore- 641105 Coimbatore- 641105

Submitted for the University Viva-Voce Examination held on…………………

INTERNALEXAMINER EXTERNALEXAMINER
ACKNOWLEDGEMENT
 ACKNOWLEDGEMENT

It is our privilege to express our gratitude to our

secretary, Shri.P.NEELARAJ and Director Dr.N.VINOTH, for their
constant inspiration and motivation to pursue this project work . It
gives us an immense pleasure to express our gratitude to our
beloved principal Dr. P. MALATHI, M.E, Ph.D, for his valuable
support and encouragement through the project work.

We wish to express our sincere thanks and gratitude to

Mr.S.MUKUNTHAN,M.TECH, Assistant Professor and Head of the
Department of Electronics and Communication Engineering for providing
invaluable insights into the subject and helping us whenever possible.

We extend our sincere thanks to Mrs.S.G.RAMA

PRIYANGA ME, Asst.Prof/ECE, Internal guide, Department of
Electronics and Communication Engineering for his valuable guidance,
suggestion and for successful completion of the project.

We wish to extend our thanks to all Teaching and non-

teaching staff members of the Department of Electronics and
Communication Engineering for their kind and patient help
throughout the project work.

We express heartfelt thanks to our parents and friends

for their support throughout our career .We would like to thank
everyone who had helped us directly and indirectly in this project
work. We thank the Lord Almighty.
 ABSTRACT

Brain tumor segmentation technology plays a pivotal role in the process of

diagnosis and treatment of MRI brain tumors. It helps doctors to locate and
measure tumors, as well as develop treatment and rehabilitation strategies.
Recently, MRI brain tumor segmentation methods based on U-Net
architecture have become popular as they largely improve the segmentation
accuracy. Meanwhile, researchers have demonstrated that introducing
attention mechanism into U-Net can enhance local feature expression and
improve the performance of medical image segmentation. In this work, we
aim to explore the effectiveness of a recent attention module called attention
gate for brain tumor segmentation task, and a novel Attention Gate Residual
U-Net model, AGResU-Net not only extracts abundant semantic information
to enhance the ability of feature learning, but also pays attention to the
information of small-scale brain tumors. The automatization of this project is
useful for post processing of the extracted region of interest like the tumor
segmentation. Magnetic Resonance Imaging is a standard modality used in
medicine for brain diagnosis and treatment. Due to the increasing of medical
data flow, the accurate detection of tumors in the MRI slices becomes a
fastidious task to perform. Furthermore the tumor detection in an image is
useful for medical experts, other purposes like segmentation and 3D
reconstruction. The manual delineation and visual inspection will be limited
in order to avoid time consumption by medical doctors. The brain tumor
tissue detection allows localizing a mass of abnormal cells in a slice of
Magnetic Resonance (MR).

i
 TABLE OF CONTENTS

CHAPTER TITLE PAGE

NO. NO.

ABSTRACT I
LIST OF FIGURES V
LIST OF ABBREVATIONS VI

1 INTRODUCTION 1
1.1 Background of the study 2
1.2 Brain tumor detection 3
2 LITERATURE SURVEY 5

2.1 Brain Tumour Image Segmentation using 6

Matlab
2.2 Review on Brain Tumor Detection Using Digital 7
Image Processing
2.3 Image Processing Techniques for Brain Tumour 7
Detection
2.4 Brain tumour MRI image segmentation and 8
detection in image processing
2.5 Application of Edge Detection for Brain Tumor 8
Detection

3 EXISTING METHOD 9
3.1 MRI segmentation methods 11
3.2 Methodology 12
3.3 Disadvantages 12

iii
 13
4 PROPOSED SYSTEM
4.1 Advantages 14
15
4.2 Brain tumor detection block diagram
4.3 Description of brain tumor 15
4.3.1 Thresholding 16
4.3.2 Algorithm implimentation 16
16
4.3.4 Preprocessing
16
4.3.5 Classifying result

17
5 SYSTEM REQUIREMENTS SPECIFICATION

5.1 Hardware requirement 18

5.2 Software requirements 18
5.2.1 MATLAB2014a 18

6 PROJECT REQUIREMENTS 19

6.1 Packages selected 20

6.1.1 Resources Requires 22
6.2 System testing 24
6.2.1 Testing objectives 24
6.2.2 Test case design 25
6.2.3 Testing strategies 26
6.3 System implementation 29
6.3.1 Software overview 29
6.3.2 Numeric computation 30
6.3.3 The Matlab language 32
6.3.4 Image acquisition 34
6.3.4.1 Image processing using Matlab 39

iv
7 RESULT AND DISCUSSION 49

7.1 Output image 50

7.1.1 Input image 51
7.1.2 Preprocessing 51
7.1.3 Morphological 52
operation 53
7.1.4 DiscreteWavelet
Transform 54
7.1.5 Segmentation
55
7.2 Summary
56

8 CONCLUSION 57

REFERENCES 59

v
 LISTOF FIGURES

FIGURENO. FIGURE NAME PAGENO.

3.2 Schematic diagram of the algorithm 12

4.3 Brain tumor detection block diagram 15

6.3.4.1 Image processing using Matlab 28

block diagram

7.2.1 Input image 51

7.2.2 Preprocessing 52

7.2.3 Morphological operation 52

7.2.4 Discrete wavelet transform 53

7.2.5.a Segmentation 54

7.2.5.b Segmentation 55

vi
 LIST OF ABBREVIATIONS

ACRONYM ABBREVIATIONS

LBP Local Binary Pattern

SVM Support Vector Machine

KNN K-Nearest Neighbor

DTC Decision Tree Classifier

GLCM Gray Level Co-

Occurance
DWT Matrix Discrete Wavelet

Transform

vii
 CHAPTER 1

INTRODUCTION

1
 CHAPTER 1

INTRODUCTION

1.1 Background of the study

Information is conveyed through images. Image processing is a process

where input image is processed to get output also as an image. Main aim of all
image processing techniques is to recognize the image or object under
consideration easier visually .All the images used in today’s world are in the
digital format. Medical images are images that show the physical attributes
distribution. Medical imaging modalities as in MRI, CT scan mostly depend on
computer technology to generate or display digital images of the internal organs
of the human body which helps the doctors to visualize the inner portions of the
body. CT scanner, Ultrasound and Magnetic Resonance Imaging took over
conventional x-ray imaging, by allowing the doctors see the body's third
dimension.Human body is made up of several types of cells.
Brain is a highly specialized and sensitive
organ of human body. Brain tumor is a very harmful disease for human being.
The brain tumor is intracranial mass made up by abnormal growth of tissue in
the brain or around the brain. Brain tumour can be detected by benign or
malignant type. The benign being non-cancerous and malignant is cancerous.
Malignant tumour is classified into two types; primary and secondary tumour
benign tumour is less harmful than malignant. The malignant tumour it spread
rapidly entering other tissues of the brain therefore, worsening condition
patients are loosed. Brain tumour detection is very challenging problem due to
complex structure of brain. Brain tumor diagnosis is quite difficult because of
diverse shape, size, location and appearance of tumor in brain. Brain Tumor
detection is very hard in beginning stage because it can’t find the accurate
measurement of tumor. But once it gets identified the brain

2
tumor it gives to start the proper treatment and it may be curable. Therefore, the
treatments depend on tumor like; chemotherapy, radiotherapy and surgery.
Medical imaging is useful to diagnose the noninvasive possibilities.

1.2 Brain tumor detection

The various types of medical imaging technologies based on noninvasive

approach like; MRI, CT scan, Ultrasound, SPECT, PET and X-ray. In the field
of medical diagnosis systems (MDS), Magnetic resonance Imaging (MRI),
gives the better results rather than Computed Tomography (CT), because
Magnetic resonance Imaging provides greater contrast between different soft
tissues of human body. In MRI-scan is a powerful magnetic fields component to
determine the radio frequency pulses and to produces the detailed pictures of
organs, soft tissues, bone and other internal structures of human body. The MRI-
Technique is most effective for brain tumor detection. The brain tumor detection
can be done through MRI images. In image processing and image enhancement
tools are used for medical image processing to improve the quality of images.
The contrast adjustment and threshold techniques are used for highlighting the
features of MRI images. The Edge detection, Histogram, Segmentation and
Morphological operations play a vital role for classification and detecting the
tumor of brain. The main objective of this paper is too studied and reviewed the
different research papers to find the various filters and segmentation techniques,
algorithms to brain tumor detection. The various steps of MR imaging like;
preprocessing, feature extraction, segmentation, post- processing, etc. which is
used for finding the tumor area of MRI-images. The working of MRI imaging is
that Protons and neutrons of the nucleus of an atom have an angular momentum
which is known as a spin. These spins will cancel when the number of
subatomic particles in a nucleus is even. Nuclei with odd number will have a
resultant spin .This forms the basis of magnetic resonance imaging. A magnetic
resonance imaging (MRI) scanner uses powerful magnets

3
to polarize and excite hydrogen nuclei (single proton) in human tissue, which
produces a signal that can be detected and it is encoded spatially, resulting in
images of the body. The MRI machine emits radio frequency (RF) pulse that
specifically binds only to hydrogen. The system sends the pulse to that specific
area of the body that needs to be examined. Due to the RF pulse, protons in that
area absorb the energy needed to make them spin in a different direction. This is
meant by the resonance of MRI. The RF pulse makes the protons spin at the
larmour frequency, in a specific direction. This frequency is found based on the
particular tissue being imaged and the strength of the main magnetic field. MRI
uses three electromagnetic fields: static field which is a very strong static
magnetic field which polarizes the hydrogen nuclei; gradient field which is a
weaker time-varying field used for spatial encoding; and a weak radio
frequency field for manipulation of the hydrogen nuclei to produce measurable
signals, which are collected through radio frequency antenna.

4
 CHAPTER 2

LITERATURE SURVEY

5
 CHAPTER 2

LITERATURE SURVEY

2.1 LITERATURE SURVEY:

1. Brain Tumour Image Segmentation using MATLAB

Brain tumour is a group of cell that grows abnormally in the cell, nerves and
other parts of the brain. Methods such as X-Ray, CT-Scan, MRI is available to
detect the brain tumour. It is necessary to find the accurate part of the affected
area of the brain tumour. Bio-medical image processing is the most challenging
and upcoming field in the present world. By using MATLAB, the tumour
present in the MRI brain image is segmented and the type of tumour is specified
using SVM classifier (Support Vector Machine). MRI of the brain for the image
segmentation using MATLAB used and specified the type of the tumour. To
segment tumour regions from MRI image, here an efficient algorithm called
threshold segmentation algorithm is used. This algorithm is mainly used for
segmentation process. It is performed by dividing the whole process into three
stages such as Pre-processing stage, Segmentation stage and Output stage. Pre-
processing stage consists of three steps. The first one is giving MRI input
image, second step is to convert it into the gray scale image and third step is to
enhance it using high pass filter. In the segmentation stage we use threshold
segmentation algorithm for segmentation of the tumour from the brain. The
third stage is the output stage where the tumour regions are segmented and
shown in output image. In this stage, we also use SVM classifier to identify the
type of tumour present in the brain.

6
2. Review on Brain Tumor Detection Using Digital Image Processing

In this paper, they describes the methodology of detection & extraction of

brain tumor from patient’s MRI scan images of the brain. A method for
segmentation of brain tumor has been developed on 2D-MRI data which allows
the identification of tumor tissue with high accuracy and reproducibility
compared to manual techniques. This method incorporates with some noise
removal functions, segmentation which are the basic concepts of image
processing. Detection and extraction of tumor from MRI scan images of the
brain is done by using MATLAB software. The aim of this work is to design an
automated tool for brain tumor quantification using MRI image data sets.

3. Image Processing Techniques for Brain Tumour Detection

MRI Imaging plays an important role in brain tumor for analysis,

diagnosis and treatment planning. It’s helpful to doctor for determine the
previous steps of brain tumor. Brain tumor detections are using MRI images is a
challenging task, because the complex structure of the brain. Brain tumor is an
abnormal growth of cell of brain. MRI images offer better difference concern of
various soft tissues of human body. MRI Image provides better results than CT,
Ultrasound, and X-ray. In this the various preprocessing, post processing and
methods like; (Filtering, contrast enhancement, Edge detection) and post
processing techniques like; (Histogram, Threshold, Segmentation operation)
through image processing (IP) tool is available in MATLAB for detection of
brain tumor images (MRI-Images).

7
4. Brain tumor MRI image segmentation and detection in image
processing

Image segmentation plays a significant role in image processing as it

helps in the extraction of suspicious regions from the medical images. In this
paper we have proposed segmentation of brain MRI image using K-means
clustering algorithm followed by morphological filtering which avoids the mis
clustered regions that can inevitably be formed after segmentation of the brain
MRI image for detection of tumor location.

5. Application of Edge Detection for Brain Tumor Detection

Brain tumors are created by abnormal and uncontrolled cell division in

brain itself. If the growth becomes more than 50%, then the patient is not able to
recover. So the detection of brain tumor needs to be fast and accurate. The
objective of this paper is to provide an efficient algorithm for detecting the
edges of brain tumor. The first step starts with the acquisition of MRI scan of
brain and then digital imaging techniques are applied for getting the exact
location and size of tumor. MRI images consist of gray and white matter and the
region containing tumor has more intensity. So, first noise filters are used for
noise removal and then enhancement techniques are applied to the given MRI
scan of brain. After that the basic morphological operations are applied for
extracting the region suffering from tumor. And then verification of region
detected is done by using watershed segmentation.

8
 CHAPTER 3

EXISTING METHOD
9
 CHAPTER 3

EXISTING METHOD

Image fusion is a process of combining complementary information from

multi modality images of the same patient in to an image. Hence the
resultant image consists of more informative than the individual images
alone. In feature level fusion, source images are segmented into regions and
features like pixel intensities, edges or texture are used for fusion..The
feature level image fusion with region based would be more meaningful than
the pixel based fusion methods. The proposed fusion method contains the
multi modal images are segmented into regions using automatic
segmentation process and the images are fused according to region based
fusion rule. A tumor cell is a form of cell that develops out of control of the
ordinary forces and standardizes growth. Braintumor is one of the major
reasons for human death every year.Around 50% of brain tumor diagnosed
patient die with primary brain tumors each year in the United States.
Electronic modalities are used to diagnose brain tumors. Among all
electronic modalities, Magnetic Resonance Imaging (MRI) is one of the
most used and popular for brain tumor diagnosis. In this research study, an
automated approach has been proposed where MRI gray-scale images were
incorporated for brain tumor detection. This study proposed an automated
approach that includes enhancement at the initial stage to minimize gray-
scale color variations. Filter operation was used to remove unwanted noises
as much as possible to assist better segmentation. As this study test grayscale
images therefore; threshold based OTSU segmentation was used instead of
color segmentation. Finally, pathology experts provided feature information
was used to identify the region of interests (brain tumor region). The
experimental results showed that the proposed approach was able to perform

10
better results compared to existing available approaches in terms of accuracy
while maintaining the pathology experts’ acceptable accuracy rate.
3.1 MRI segmentation methods
Two different MRI segmentation methods that use multispectral image data
are proposed for the estimation of the volume of brain tumors. A supervised
k-nearest neighbor (kNN) and a semi-supervised fuzzy c-means (SFCM)
pattern recognition methods are used for the image segmentation. The
reproducibility of the two methods in determining the volume of different
tumors and the change in volume with therapy are estimated. The results are
compared with the volume estimates obtained by gray-level based seed-
growing method that is being used clinically. The results indicate that kNN
and SFCM methods should provide an accurate and reliable image
segmentation and tumor volume estimate, as required for treatment planning
and surgery simulation.
Tissue segmentation based on 2D and 3D feature maps derived from high
resolution MR images was performed in experimental brain edema in cats,
normal humans and those with brain tumors and MS. Statistical and
anisotropic diffusion filters were applied to the data. The k-nearest
neighborhood segmentation algorithm was utilized. Segmentation based on a
3D feature map was found to be much better than that based on a 2D feature
map (p<0.01). Inter-observer variability ranged between 6.6% and 9.3% and
intra-observer variability ranged between 8.3% and 10.4%. The use of high
resolution MRI resulted in detection of new lesions which well correlated
with neuropsychological exams. In conclusion, the presented technique is an
accurate, stable and promising method of tissue characterization

11
 3.2 METHODOLOGY

FIG.3.2. Schematic diagram of the algorithm

In this section, the procedures segmentation of MRI Scan Brain tumor is

represented.The method for MRI Scan Brain tumor segmentation that involves
median filtering, threshold, largest contour, watershed segmentation, and crop.
The procedure is described in a schematic diagram shown in FIG.3.2.

3.3 DISADVANTAGES

Fusion system passes information within each decomposition level so that

the details of the source image is preserved expressing theartifacts.
It is difficult to determine whether narrowing of a spinal canal is caused
by a tissue or bone.

12
 CHAPTER 4

PROPOSED SYSTEM

13
 CHAPTER 4

PROPOSED SYSTEM

In Proposed, SVM Classifier used to segment the cancer detectedportion.

To segment the portion, first have to filter out the acquired image based
upon the masking methodology.
The Morphological function including dilation and erosion method will
be applied extracted throughout the filtered image. By the method of
morphological bounding box will be drawn over the affectedportion.
Then, the region enclosed by bounding box will be splitted out separately
with the SVM Classifier.

4.1 ADVANTAGES

Sensitivity to noise, blurring effects and miss registration.

Due to the SVM Classifier usage the starting stage of brain
Tumor will be find out

Method which uses the kernel trick,so you can build in expert
knowledge about the problem via engineering the kernel.

It is an approximation to a bound on the test error rate, and

there is a s ubstantial body of theory behind it which suggest
it should be a good idea

14
 4.2 BRAIN TUMOR DETECTION BLOCK DIAGRAM

Image Acquisition
Image
Acquisition RGB to gray
conversion

Thresholding

Tumor detection

Morphological operation

SVM classifier

Tumor detection

FIG4.2 Brain tumor detection

A simple block diagram that explains the fundamental steps of digital image
processing. Image acquisition could be as simple as being given an image that is
already in digital form. Generally, the image acquisition stage involves per-
processing, such as scaling,

4.3 DESCRIPTION :

4.3.1 IMAGE ACQUISITION:

There is a dataset consists of brain tumour (Benign (Non-cancerous) and

Malignant (Cancerous)). Among those images select anyone of the image to
classify.
.

15
4.3.2 THRESHOLDING:

Thresholding is a technique for adjusting image intensities to enhance

contrast. Because of this enhancement visual quality will be little bit better and
easy to analysis. The values will be varied up to 256.

4.3.3 ALGORITHM IMPLEMENTATION:

Algorithm is Thresholding used to classify the morphological technique

and features will be extracted.

4.3.4 PREPROCESSING:

In preprocessing, two plane conversions is done by converting into gray

format if the taken image as supposed to be three plane image

4.3.5 CLASSIFYING RESULT:

By using morphology technique the noises will be reduced for the

classified images and we will obtain as desired one and text will be used to
mention the classified type on images.

16
 CHAPTER 5

SYSTEM REQUIREMENTS SPECIFICATION

17
 CHAPTER 5

SYSTEM REQUIREMENTS SPECIFICATION

5.1 HARDWARE REQUIREMENTS

➢ HDD:>90GB
➢ PROCESSOR: >Pentium IV 2.4GHz
➢ SYSTEM TYPE: 32bit / 64 bit
➢ RAM:>2GB
➢ OS: WINDOWS 7/8/8.1/10

5.2 SOFTWARE REQUIREMENTS

➢ TOOL : MATLAB 2014a

➢ TOOL BOX : Image Processing Tool Box

5.2.1 MATLAB2014a

MATLAB, the language of technical computing, is a programming

environment for algorithm development, data analysis, visualization, and numeric
computation. Simulink is a graphical environment for simulation and Model-Based
Design for multi domain dynamic and embedded systems. Engineers and scientists
worldwide rely on these product families to accelerate the pace of discovery,
innovation, and development in automotive, aerospace, electronics, financial
services, biotech- pharmaceutical, and other industries. MATLAB and Simulink are
also fundamental teaching and research tools in the world's universities and learning
institutions

18
 CHAPTER 6

PROJECT REQUIREMENTS

19
 CHAPTER 6

PROJECT REQUIREMENTS

6.1 PACKAGES SELECTED:

The package selected to develop watermarking is MATLAB and the

package has more advanced features. As the system is to be developed in
Watermarking, MATLAB platform with windows Application is preferred.

FEATURES OF WINDOWS XP PROFESSIONAL:

The ability to become part of a Windows Server domain, a group of computers
that are remotely managed by one or more central servers.A sophisticated
access control scheme that allows specific permissions on files to be granted to
specific users under normal circumstances. However, users can use tools other
than Windows Explorer (like cacls or File Manager), or restart to Safe Mode to
modify access control lists. Remote Desktop server, which allows a PC to be
operated by another Windows XP user over a local area network or the Internet.
Offline Files and Folders, which allow the PC to automatically store a copy of
files from another networked computer and work with them while disconnected
from the network. Encrypting File System, which encrypts files stored on the
computer's hard drive so they cannot be read by another user, even with
physical access to the storage medium. Centralized administration features,
including Group Policies, Automatic Software Installation and Maintenance,
Roaming User Profiles, and Remote Installation Service (RIS). Support for two
physical central processing units (CPU). (Because the number of CPU cores and
Hyper-threading capabilities on modern CPUs are considered to be part of a
single physical processor, multi core CPUs is supported using XP Home
Edition.)Windows Management Instrumentation Console (WMIC): WMIC is a
command-line tool designed to ease WMI information retrieval about a system
by using simple keywords (aliases).

20
6.1.1 RESOURCES REQUIRED:

In this phase it is necessary to analyze the availability of the resources

that are required to design, develop, Implement and Test the project. The
resources to be analyzed are Manpower, Time and the system Requirements.
Teams of two members are involved in the entire SDLC life cycle except the
testing phase. The testing phase is guided by the professional testers before the
implementation of the product. Time Analyzed to complete the project is
approximately four months with 4 hrs on daily basis except weekends. System
requirements are analyzed and listed below.

FEASIBLITY STUDY:

The objective of feasibility study is not only to solve the problem but
also to acquire a sense of its scope. During the study, the problem definition was
crystallized and aspects of the problem to be included in the system are
determined. Consequently benefits are estimated with greater accuracy at this
stage. The key considerations are:

✓ Economicfeasibility
✓ Technicalfeasibility
✓ Operational feasibility

Economic Feasibility:

Economic feasibility studies not only the cost of hardware, software is

included but also the benefits in the form of reduced costs are considered here.
This project, if installed will certainly be beneficial since there will be reduction
in manual work and increase in the speed of work.

21
Technical Feasibility:

Technical feasibility evaluates the hardware requirements, software

technology, available personnel etc., as per the requirements it provides
sufficient memory to hold and process.

Operational Feasibility:

This is the most important step of the feasibility study this study helps to
predict the operational ability of the system that is being developed. This study
also helps to analyze the approach towards which the system must be developed
by which development effort is reduced. Proposed system is beneficial only if
they can be turned into information systems that will meet the organization
requirements. This system supports in producing good results and reduces
manual work. Only by spending time to evaluate the feasibility, do we reduce
the chances from extreme embarrassments at larger stager of the project. Effort
spend on a feasibility analysis that results in the cancellation of a proposed
project is not a wasted effort.
practices. Grain grading and specification system assures that a particular lot of
grain meets the required set standards customer. In many countries grading of
grain depends on four main properties; (i) test weight (ii) moisture contents (iii)
broken foreign material or the percentage fragments example broken corn
foreign materials (iv) damaged kernels (i.e. total and heat damaged). There is no
proper definition or description of rice quality, because as definition of quality,
depends on several factors such cooking practice and region and usages for
example rice miller he/she describe rice quality in terms of total recovery and or
head and broken rice kernels while food processing will define concept of rice
quality in terms of grain size, aroma, appearance and cook ability. Common
physical properties of rice are size, shape, color, uniformity, and general
appearance. Other factors contributes to general appearance of rice are

22
cleanliness, free from other seeds, virtuousness, translucency, chalkiness, color,
damaged and imperfect kernel. For the case of grain size, rice grain can be
categories into three main groups (i) length (ii) shape and (iii) weight.

EXISTING METHOD:

Image fusion is a process of combining complementary information from

multi modality images of the same patient in to an image. Hence the resultant
image consists of more informative than the individual images alone. In feature
level fusion, source images are segmented into regions and features like pixel
intensities, edges or texture are used for fusion.
The feature level image fusion with region based would be more
meaningful than the pixel based fusion methods. The proposed fusion method
contains the multi modal images are segmented into regions using automatic
segmentation process and the images are fused according to region based fusion
rule.

DISADVANTAGES:

➢ Fusion system passes information within each decomposition level so that

the details of the source image is preserved expressing theartifacts.
➢ It is difficult to determine whether narrowing of a spinal canal is caused
by a tissue or bone.

PROPOSED METHOD:
In Proposed, SVM Classifier used to segment the cancer detected portion.
To segment the portion, first have to filter out the acquired image based upon
the masking methodology. The Morphological function including dilation and
erosion method will be applied extracted throughout the filtered image. By the
method of morphological bounding box will be drawn over the affectedportion.

23
Then, the region enclosed by bounding box will be splitted out separately with
the SVM Classifier.

ADVANTAGES:
➢ Sensitivity to noise, blurring effects and miss registration.
➢ Due to the SVM Classifier usage the starting stage of brain tumor will be
find out.
➢ Method which uses the kernel trick, so you can build in expert knowledge
about the problem via engineering thekernel.
➢ It is an approximation to a bound on the test error rate, and there is a
substantial body of theory behind it which suggests it should be a good
idea.

6.2 SYSTEM TESTING:

6.2.1 TESTING OBJECTIVES:

Testing is a set of activities that can be planned in advance and conducted

systematically. For this reason a template for software testing, a set of steps into
which we can place specific test case design techniques and testing methods
should be defined for software process. Testing often accounts for more effort
than any other software engineering activity. If it is conducted haphazardly,
time is wasted, unnecessary effort is expanded, and even worse, errors sneak
through undetected. It would therefore seem reasonable to establish a systematic
strategy for testing software.

Type of Testing:

There are two type of testing according their behaviors

1. Unconventional Testing

24
 2. Conventional Testing

Unconventional Testing:

Unconventional testing is a process of verification which is doing by

SQA (Software Quality Assurance) team. It is a prevention technique which is
performing from begging to ending of the project development. In this process
SQA team verifies project development activities and insuring that developing
project is fulfilling the requirement of the client or not.

In this testing the SQA team follows these methods:

1. Peer review

2. Code walk and throw

3. Inspection

4. Document Verification

Conventional Testing:

Conventional Testing is a process of finding the bugs and validating the

project. Testing team involves in this testing process and validating that
developed project is according to client requirement or not. This process is a
correction technique where testing team find bugs and reporting to the
development team for correction on developed project built.

6.2.2 TEST CASE DESIGN:

Unit Testing:

The primary goal of unit testing is to take the smallest piece of testable
software in the application, isolate it from the remainder of the code, and
determine whether it behaves exactly as you expect. Each unit is tested
separately before integrating them into modules to test the interfaces between

25
modules. Unit testing has proven its value in that a large percentage of defects
are identified during its use. In the company as well as seeker registration form,
the zero length username and password are given and checked. Also the
duplicate username is given and checked. In the job and question entry, the
button will send data to the server only if the client side validations are made.
The dates are entered in wrong manner and checked. Wrong email-id and web
site URL (Universal Resource Locator) is given and checked.

Integration Testing:

Testing is done for each module. After testing all the modules, the
modules are integrated and testing of the final system is done with the test data,
specially designed to show that the system will operate successfully in all its
aspects conditions. Thus the system testing is a confirmation that all is correct
and an opportunity to show the user that the system works.

Validation Testing:

The final step involves Validation testing, which determines whether the
software function as the user expected. The end-user rather than the system
developer conduct this test most software developers as a process called “Alpha
and Beta Testing” to uncover that only the end user seems able to find. The
compilation of the entire project is based on the full satisfaction of the end
users. In the project, validation testing is made in various forms. In question
entry form, the correct answer only will be accepted in the answer box. The
answers other than the four given choices will not beaccepted.

6.2.3 TESTING STRATEGIES

A number of software testing strategies have been proposed in the

literature. All provide the software developer with a template for testing and all
have the following generic characteristics:

26
 1. Testing begins at the component level and works “outward” toward the
integration of the entire computer-based system.
2. Different testing techniques are appropriate at different points intime.
3. The developer of the s/w conducts testing and for large projects,
independent test group.
4. Testing and debugging are different activities, but debugging must be
accommodated in any testing strategy.

Integration Testing:

The strategies for integrating software components into a functioning

product include the bottom-up strategy, the top-down strategy and to ensure that
modules will be available for integration into the evolving software product
when needed. The integration strategy dictates the order in which modules must
be available and thus exerts a strong influence on the order in which modules
are written, debugged and unit tested.

White Box Testing:

It is just the vice versa of the Black Box testing. There we do not watch
the internal variables during testing. This gives clear idea about what is going
on during execution of the system. The point at which the bug occurs were all
clear and were removed.

Black Box Testing:

In this testing we give input to the system and test the output. Here we do
not go for watching the internal file in the system and what are the changes
made on them for the required output.

27
Interface Testing

The Interface Testing is performed to verify the interfaces between sub

modules while performing integration of sub modules aiding master module
recursively.

Module Testing

Module Testing is a process of testing the system, module by module. It

includes the various inputs given, outputs produced and their correctness. By
testing in this method we would be very clear of all the bugs that have occurred.

Maintenance

The objectives of this maintenance work are to make sure that the system
gets into work all time without any bug. Provision must be for environmental
changes which may affect the computer or software system. This is called the
maintenance of the system. Nowadays there is the rapid change in the software
world. Due to this rapid change, the system should be capable of adapting these
changes. In our project the process can be added without affecting other parts of
the system. Maintenance plays a vital role. The system will able to accept any
modification after its implementation. This system has been designed to favour
all new changes. Doing this will not affect the system’s performance or its
accuracy. This is the final step in system life cycle. Here we implement the
tested error-free system into real-life environment and make necessary changes,
which runs in an online fashion.

28
6.3 SYSTEM IMPLEMENTATION:
6.3.1 SOFTWARE OVERVIEW

MATLAB is a high-level language and interactive environment for

numerical computation, visualization, and programming. Using MATLAB, you
can analyze data, develop algorithms, and create models and applications. The
language, tools, and built-in math functions enable you to explore multiple
approaches and reach a solution faster than with spreadsheets or traditional
programming languages, such as C/C++ or Java You can use MATLAB for a
range of applications, including signal processing and communications, image
and video processing, control systems, test and measurement, computational
finance, and computational biology. More than a million engineers and
scientists in industry and academia use MATLAB, the language of technical
computing.

Key Features

• High-level language for numerical computation, visualization, and

application development
• Interactive environment for iterative exploration, design, and problem
solving
• Mathematical functions for linear algebra, statistics, Fourier analysis,
filtering, optimization, numerical integration, and solving ordinary
differential equations
• Built-in graphics for visualizing data and tools for creating customplots
• Development tools for improving code quality and maintain ability and
maximizing Performance
• Tools for building applications with custom graphical interfaces.
• Functions for integrating MATLAB based algorithms with external
applications and Languages such as C, Java, .NET, and MicrosoftExcel

29
6.3.2 NUMERIC COMPUTATION

MATLAB provides a range of numerical computation methods for

analyzing data, developing algorithms, and creating models. The MATLAB
language includes mathematical functions that support common engineering and
science operations

Core math functions use processor-optimized libraries to provide fast

execution of vector and matrix calculations.

Available methods include:

• Interpolation and regression

• Differentiation and integration

• Linear systems of equations

• Fourier analysis

• Eigen values and singular values

• Ordinary differential equations (ODEs)

• Sparse matrices

MATLAB add-on products provide functions in specialized areas such as

statistics, optimization, signal analysis, and machine learning

Data Analysis and Visualization

MATLAB provides tools to acquire, analyze, and visualize data, enabling

you to gain insight into your data in a fraction of the time it would take using
spreadsheets or traditional programming languages. You can also document and
share your results through plots and reports or as published MATLAB code

30
Acquiring Data

MATLAB lets you access data from files, other applications, databases,
and external devices. You can read data from popular file formats such as
Microsoft Excel; text or binary files; image, sound, and video files; and
scientific files such as net CDF and HDF. File I/O functions let you work with
data files in any format.

Using MATLAB with add-on products, you can acquire data from
hardware devices, such as your computer’s serial port or sound card, as well as
stream live, measured data directly into MATLAB for analysis and
visualization. You can also communicate with instruments such as
oscilloscopes, function generators, and signal analyzers.

Analyzing Data

MATLAB lets you manage, filter, and preprocess your data. You can
perform exploratory data analysis to uncover trends, test assumptions, and build
descriptive models. MATLAB provides functions for filtering and smoothing,
interpolation, convolution, and fast Fourier transforms (FFTs). Add-on products
provide capabilities for curve and surface fitting, multivariate statistics, spectral
analysis, image analysis, system identification, and other analysis tasks.

Visualizing Data

MATLAB provides built-in 2-D and 3-D plotting functions, as well as

volume visualization functions. You can use these functions to visualize and
understand data and communicate results. Plots can be customized either
interactively or programmatically. The MATLAB plot gallery provides
examples of many ways to display data graphically in MATLAB. For each
example, you can view and download source code to use in your MATLAB
application.

31
Documenting and Sharing Results

You can share results as plots or complete reports. MATLAB plots can be
customized to meet publication specifications and saved to common graphical
and data file formats. You can automatically generate a report when you
execute a MATLAB program. The report contains your code, comments, and
program results, including plots. Reports can be published in a variety of
formats, such as HTML, PDF, Word, or Latex.

Programming and Algorithm Development

MATLAB provides a high-level language and development tools that let

you quickly develop and analyze algorithms and applications.

6.3.3 THE MATLAB LANGUAGE

The MATLAB language provides native support for the vector and
matrix operations that are fundamental to solving engineering and scientific
problems, enabling fast development and execution. With the MATLAB
language, you can write programs and develop algorithms faster than with
traditional languages because you do not need to perform low-level
administrative tasks such as declaring variables, specifying data types, and
allocating memory. In many cases, the support for vector and matrix operations
eliminates the need for for-loops. As a result, one line of MATLAB code can
often replace several lines of C or C++ code. MATLAB provides features of
traditional programming languages, including f low control, error handling, and
object-oriented programming (OOP). You can use fundamental data types or
advanced data structures, or you can define custom data types. You can produce
immediate results by interactively executing commands one at a time. This
approach lets you quickly explore multiple options and iterate to an optimal
solution. You can capture interactive steps as scripts and functions to reuse and
automate your work. MATLAB add-on products provide built-in algorithmsfor

32
signal processing and communications, image and video processing, control
systems, and many other domains. By combining these algorithms with your
own, you can build complex programs and applications.

Development Tools

MATLAB includes a variety of tools for efficient algorithm development,

including:

Command Window –Lets you interactively enter data, execute commands and
programs, and display results

MATLAB Editor–Provides editing and debugging features, such as setting

break points and stepping through individual lines of code

Code Analyzer–Automatically checks code for problems and recommends

modifications to maximize performance and maintainability

MATLAB Profiler–Measures performance of MATLAB programs and

identifies areas of code to modify for improvement

Additional tools compare code and data files, and provide reports
showing file dependencies, annotated reminders, and code coverage.

33
Integration with Other Languages and Applications

You can integrate MATLAB applications with those written in other

languages.

From MATLAB, you can directly call code written in C, C++, Java, and
.NET. Using the MATLAB engine library, you can call MATLAB code from C,
C++, or FORTRAN applications.

Performance

MATLAB uses processor-optimized libraries for fast execution of matrix

and vector computations. For general-purpose scalar computations, MATLAB
uses its just-in-time (JIT) compilation technology to provide execution speeds
that rival those of traditional programming languages. To take advantage of
multi core and multiprocessor computers, MATLAB provides many
multithreaded linear algebra and numerical functions. These functions
automatically execute on multiple computational threads in a single MATLAB
session, enabling them to execute faster on multi core computers You can take
further advantage of multi core desktop and other high-performance computing
resources such as GPUs and clusters with add-on parallel computing products.
These products provide high-level constructs that let you parallelize
applications with only minor changes to MATLAB code.

6.3.4 IMAGE ACQUISITION

Image Acquisition Toolbox™ enables you to acquire images and video

from cameras and frame grabbers directly into MATLAB and SIMULINK. You
can detect hardware automatically and configure hardware properties. Advanced
workflows let you trigger acquisition while processing in-the-loop, perform
background acquisition, and synchronize sampling across several multimodal
devices. With support for multiple hardware vendors and industry standards,

34
you can use imaging devices ranging from inexpensive Web cameras to high-
end

Key features

• Support for industry standards, including DCAM, Camera Link, and

GigE Vision
• Support for common OS interfaces for webcams, including Direct Show,
QuickTime, and video4linux2
• Support for a range of industrial and scientific hardware vendors
• Multiple acquisition modes and buffer management options
• Synchronization of multimodal acquisition devices with hardware
triggering
• Image Acquisition app for rapid hardware configuration, image
acquisition, and live video previewing
• Support for C code generation in Simulink

Together, MATLAB, Image Acquisition Toolbox, and Image Processing

Toolbox™ (and, optionally, Computer Vision System Toolbox™) provide a
complete environment for developing customized imaging solutions. You can
acquire images and video, visualize data, develop processing algorithms and
analysis techniques, and create Ui's and apps. The image acquisition engine
enables you to acquire frames as fast as your camera and PC can support for
high speed imaging. In addition, you can use Image Acquisition Toolbox with
Simulink and Computer Vision System Toolbox to model and simulate real-
time embedded imaging systems.

35
 Image Acquisition Toolbox simplifies the acquisition process by
providing a consistent interface across operating systems, hardware devices, and
vendors. The toolbox provides multiple ways to access hardware devices from
MATLAB and Simulink: the Image Acquisition Tool, a programmatic interface
in MATLAB, and a block for Simulink. Each workflow provides access to
camera properties and controls while enabling you to solve different types of
problems with the strengths of each environment

App for Image and Video Acquisition

The Image Acquisition app enables you to work with image and video
acquisition devices and is well suited for interactive configuration of cameras.
You can browse all hardware devices available on your computer, change
device settings, select a region of interest (ROI), preview an acquisition, acquire
images and video, and record data. A preview window helps verify and
optimize your acquisition parameters by automatically reflecting any
adjustments made to camera properties in the video stream. The Image
Acquisition app serves as a starting point in the development of automated and
custom image acquisition and processing systems.

Session Logging

Session logging lets you track actions performed in the tool with a history of
command-line equivalent functions. In situations that require the same
configuration and control process for multiple trials and experiments, the
session log provides the ability to load settings to a common point and export
the code to a programmatic interface in MATLAB for furtherautomation.

36
Data Logging and Export

You can log data to disk, memory, or both simultaneously with the Image
Acquisition app or programmatically at the MATLAB command line. You can
set a limit on memory usage to prevent overuse of resources in memory-
intensive applications. Data acquired with the tool can also be exported directly
to the Image Viewer app in Image Processing Toolbox for greater control over
visualization. In addition, you can:

• Log each image frame or log frames at specified intervals

• Log data to disk as compressed or uncompressed AVI streams and MAT-
files
• Specify frame rate, compression techniques, and key frame rate for AVI
streams
• Extract single images from a video stream and store them in standard
formats, including JPEG 2000, BMP, JPEG, and TIFF

Image Acquisition in MATLAB

Image Acquisition Toolbox provides an app and functions and a

programmatic interface to help you work with image acquisition hardware in
MATLAB. You can automate repetitive tasks, create workflows combined with
tasks such as image processing, and create standalone executables that acquire
images and video with MATLAB COMPILER. The toolbox enables you to
customize the acquisition process to include integrating image processing
functionality to identify objects, enhance imagery, or construct mosaics and
panoramic views as the data is acquired. Image of blister packs acquired by
Image Acquisition Toolbox. Image Processing Toolbox analyzes the data and
marks broken pills.

37
Connecting to Hardware

Image Acquisition Toolbox automatically detects compatible image and

video acquisition devices. Each device connection is encapsulated as an object,
providing an interface for configuration and acquisition. You can create
multiple connection objects for simultaneous acquisition from as many devices
as your PC and imaging hardware support. Image Acquisition Toolbox can be
used on Windows®, Linux®, and Macintosh® systems, enabling you to reuse
code when connecting to the same camera in different operating systems.
Scientific camera connected to a laptop to acquire images of a scene. The
images are acquired using Image Acquisition Toolbox and analyzed using
Image Processing Toolbox.

Acquiring Image Data

Image Acquisition Toolbox supports several modes, including

background acquisition and continuous acquisition, while processing the
acquired data. The toolbox automatically buffers data into memory, handles
memory and buffer management, and enables acquisition from an ROI. The
image acquisition engine is designed to acquire imagery as fast as your camera
and computer can support, enabling analysis and processing of high-speed
imaging applications.

Data can be acquired in a wide range of data types, including signed or

unsigned 8-, 16-, and 32-bit integers and single- or double-precision floating
point. The toolbox supports any color space provided by the image acquisition
device including RGB, YUV, or grayscale. Raw sensor data in a Bayer pattern
can be automatically converted into RGB data.

38
Extensible Hardware Support

Image Acquisition Toolbox supports several industry standards including

DCAM, Camera Link, and GigE Vision digital interfaces, as well as common
interfaces including DirectShow, QuickTime, and video4linux2. The toolbox is
also supported across Windows, Linux, and Macintosh systems, enabling you to
reuse code and transition designs to other systems. In addition, the toolbox
provides specific support for some manufacturers, enabling proprietary features
and increasing performance in image acquisition.

Adaptor Kit

Advanced users who want to customize or connect to different cameras

can extend support through adaptors connecting the toolbox with third-party
drivers. An adaptor is a communication layer between the Image Acquisition
Toolbox acquisition engine and a third-party SDK and drivers. The adaptor
enables access to proprietary camera features that may not be available through
industry standards, improves camera performance, and enables logging and
triggering options. The toolbox documentation provides an adaptor kit and
example code detailing the development process.

Building an adaptor typically requires extensive knowledge of a vendor’s

SDK; as a result, several manufacturers have written adaptors in partnership
with Math Works and made them available on their Web sites. Visit the
supported hardware page for more information on available adaptors and to
request support for specific hardware vendors.

6.3.4.1 Image processing using MATLAB:

Image processing is a form of signal processing, which uses image as

input and output. Generally, an image can be of two or three dimensional array.
39
In MATLAB, this array or matrix is manipulated. The picture shown below
defines you the several stages of image processing in MATLAB.

FIG.6.3.4.1 Block diagram of image processing in matlab

An image acquisition device can be a video camera, which is used for

capturing images. The image captured either with the help of digital or analogue
cameras can be used as the input. Most importantly, these cameras should be
capable of delivering images at different resolutions.

Digital cameras like CCD or CMOS sensor are those which have the
direct connection with the PC using USB port. Meanwhile, analogue cameras
require a grabbing card for connecting with PC. In MATLAB, Augmented
Reality is currently used for capturing the live video streams of the real world. It
is directly interfaced with the PC (Image Processor), and MATLAB uses inbuilt
software called adaptors for accessing or communicating with thisdevice.

Image analysis can be done by extracting some of the functional details

from the captured images. Therefore, if there is a requirement for identifying an
object, then several robust characteristics of an object like color, pattern, edges,
intensity, and structure must be noted.

40
 The final stage of image processing is the machine control in which a
robot is controlled according to the details obtained from image analysis. For
example, if a robot needs to identify a ball, it captures images in front of it,
sends it to PC, and analyses it with the MATLAB program. If the image input
and program output are satisfied, then it detects it as a ball. Otherwise, it goes
on searching for a ball by this method.

Overall, MATLAB is used in robots for detecting or tracking an image by

determining some of the parameters like location, size, shape, contour, etc., and
planning decisions based on it.

Key Features

• Image enhancement, filtering, and deblurring

• Image analysis, including segmentation, morphology, feature extraction,
and measurement
• Geometric transformations and intensity-based image registration
methods/li>
• Image transforms, including FFT, DCT, Radon, and fan-beamprojection
• Workflows for processing, displaying, and navigating arbitrarily large
images
• Image Viewer and Video Viewer apps
• DICOM import and export

Importing and Exporting Images

Image Processing Toolbox supports images generated by a wide range of

devices, including digital cameras, satellite and airborne sensors, medical
imaging devices, microscopes, telescopes, and other scientific instruments. You
can visualize, analyze, and process these images in many data types, including

41
single-precision and double-precision floating-point and signed and unsigned 8-
bit, 16-bit, and 32-bit integers.

There are several ways to import and export images into and out of the
MATLABenvironment for processing. You can use Image Acquisition Toolbox
to acquire live images from Web cameras, frame grabbers, DCAM cameras,
GigE Vision cameras, and other devices. Using Database Toolbox , you can
access images stored in ODBC-compliant or JDBC-compliant databases.

Standard and Specialized Formats Supported

MATLAB supports standard data and image formats, including JPEG,

JPEG-2000, TIFF, PNG, HDF, HDF-EOS, FITS, Microsoft® Excel®, ASCII,
and binary files. It also supports the multiband image formats BIP and BIL, as
used by LANDSAT. Low-level I/O and memory mapping functions enable you
to develop custom routines for working with any data format.

Image Processing Toolbox supports a number of specialized image file

formats. For medical images, it supports DICOM files, including associated
metadata, as well as the Analyze 7.5 and Interfile formats. The toolbox can also
read geospatial images in NITF files and high dynamic range images in HDR
files.

Pre processing and Post processing Images

Image Processing Toolbox provides reference-standard algorithms for

preprocessing and post processing tasks that solve frequent system problems,
such as interfering noise, low dynamic range, out-of-focus optics, and the
difference in color representation between input and output devices.

42
Image Enhancement

Image enhancement techniques in Image Processing Toolbox enable you to

increase the signal-to-noise ratio and accentuate image features by modifying
the colors or intensities of an image. You can:

• Perform histogram equalization

• Perform decor relation stretching
• Remap the dynamic range
• Adjust the gamma value
• Perform linear, median, or adaptive filtering

The toolbox includes specialized filtering routines and a generalized

multidimensional filtering function that handles integer image types, offers
multiple boundary-padding options, and performs convolution and correlation.
Predefined filters and functions for designing and implementing your own linear
filters are also provided.

Contrast Enhancement Techniquesenhancinggrayscale and true color images

with adaptive histogram equalization.

Image Deblurring

Image deblurring algorithms in Image Processing Toolbox include blind,

Lucy-Richardson, Wiener, and regularized filter deconvolution, as well as
conversions between point spread and optical transfer functions. These
functions help correct blurring caused by out-of-focus optics, movement by the
camera or the subject during image capture, atmospheric conditions, short
exposure time, and other factors. All deblurring functions work with
multidimensional images.

43
Deblurring Images Using a Regularized Filterrestoring a blurred and noisy
image using a constrained least square restoration algorithm.

Deblurring Images Using the Blind DeconvolutionAlgorithmrestoring an

image when no information about the distortion is available.

Device-Independent Color Management

Device-independent color management in Image Processing Toolbox

enables you to accurately represent color independently from input and output
devices. This is useful when analyzing the characteristics of a device,
quantitatively measuring color accuracy, or developing algorithms for several
different devices. With specialized functions in the toolbox, you can convert
images between device-independent color spaces, such as sRGB, XYZ, xyY,
L*a*b*, uvL, and L*ch.

Color-Based Segmentation Using the L*a*b* Color Spaceidentifying

different colors by analyzing an image in an alternative color space.

For more flexibility and control, the toolbox supports profile-based color
space conversions using a color management system based on ICC version 4.
For example, you can import n-dimensional ICC color profiles, create new or
modify existing ICC color profiles for specific input and output devices, specify
the rendering intent, and find all compliant profiles on your machine.

Image Transform

Image transforms such as FFT and DCT play a critical role in many
image processing tasks, including image enhancement, analysis, restoration, and
compression. Image Processing Toolbox provides several image transforms,
including Radon and fan-beam projections. You can reconstruct images from
parallel-beam and fan-beam projection data (common in tomography

44
applications). Image transforms are also available in MATLAB and Wavelet
Toolbox™.

Reconstructing an Image from Projection Datacomparing the reconstruction

of an image using parallel (Radon) and fan-beam geometries.

Image Conversion

Image conversions between data classes and image types are a common
requirement for imaging applications. Image Processing Toolbox provides a
variety of utilities for conversion between data classes, including single- and
double-precision floating-point and signed or unsigned 8-, 16-, and 32-bit
integers. The toolbox includes algorithms for conversion between image types,
including binary, grayscale, indexed color, and truecolor. Specifically for color
images, the toolbox supports a variety of color spaces (such as YIQ, HSV, and
YCrCb) as well as Bayer pattern encoded and high dynamic range images.

Neural Network Toolbox

Neural Network Toolbox™ provides functions and apps for modeling

complex nonlinear systems that are not easily modeled with a closed-form
equation. Neural Network Toolbox supports supervised learning with
feedforward, radial basis, and dynamic networks. It also supports unsupervised
learning with self-organizing maps and competitive layers. With the toolbox
you can design, train, visualize, and simulate neural networks. You can use
Neural Network Toolbox for applications such as data fitting, pattern
recognition, clustering, time-series prediction, and dynamic system modeling
and control.

45
 To speed up training and handle large data sets, you can distribute
computations and data across multicore processors, GPUs, and computer
clusters using Parallel Computing Toolbox™.

Key Features

• Supervised networks, including multilayer, radial basis, learning vector

quantization (LVQ), time-delay, nonlinear autoregressive (NARX), and
layer-recurrent
• Unsupervised networks, including self-organizing maps and competitive
layers
• Apps for data-fitting, pattern recognition, and clustering
• Parallel computing and GPU support for accelerating training (using
Parallel Computing Toolbox)
• Preprocessing and post processing for improving the efficiency of
network training and assessing network performance
• Modular network representation for managing and visualizing networks
of arbitrary size
• Simulink blocks for building and evaluating neural networks and for
control systems applications

Network Architectures

Neural Network Toolbox supports a variety of supervised and

unsupervised network architectures. With the toolbox’s modular approach to
building networks, you can develop custom network architectures for your
specific problem. You can view the network architecture including all inputs,
layers, outputs, and interconnections.

46
Supervised Networks

Supervised neural networks are trained to produce desired outputs in

response to sample inputs, making them particularly well-suited to modeling
and controlling dynamic systems, classifying noisy data, and predicting future
events.

Neural Network Toolbox includes four types of supervised networks:

feed forward, radial basis, dynamic and learning vector quantization.

Feed forward networks have one-way connections from input to output layers.
They are most commonly used for prediction, pattern recognition, and nonlinear
function fitting. Supported feed forward networks include feed forward back
propagation, cascade-forward back propagation, feed forward input-delay back
propagation, linear, and perception networks.

A two-layer feed forward network with sigmoid hidden neurons and

linear output neurons. This type of network can fit multidimensional mapping
problems arbitrarily well, given consistent data and enough neurons in its
hidden layer.

Radial basis networks provide an alternative, fast method for designing

nonlinear feed forward networks. Supported variations include generalized
regression and probabilistic neural networks.

Dynamic networks use memory and recurrent feedback connections to

recognize spatial and temporal patterns in data. They are commonly used for
time-series prediction, nonlinear dynamic system modeling, and control systems
applications. Prebuilt dynamic networks in the toolbox include focused and
distributed time-delay, nonlinear autoregressive (NARX), layer-recurrent,

47
Elman, and Hopfield networks. The toolbox also supports dynamic training of
custom networks with arbitrary connections.

Maglev Modeling with Neural Time Series AppModel the position of a

levitated magnet as current passes through an electromagnet beneath it.

Learning vector quantization (LVQ) networks use a method for classifying

patterns that are not linearly separable. LVQ lets you specify class boundaries
and the granularity of classification.

Unsupervised Networks

Unsupervised neural networks are trained by letting the network continually

adjust itself to new inputs. They find relationships within data and can
automatically define classification schemes.

48
 CHAPTER 7

RESULT AND DISCUSSION

49
 CHAPTER 7
RESULT AND DISCUSSION

Brain tumor is an abnormal growth of cells within the brain or in the central
spinal canal. This system was tested to show performance of extensive
calculations of brain tumor area and brain area. The area of brain tumor is
obtained by counting the number of tumor pixels.Then calculation of the
average error value of brain tumors area and brain area. Error testing of tumor
extent is used to test how effective segmentation has been done. The first step
to start performing brain tumors is preprocessing first using the median
filtering. Median fitering works by moving the pixel value of the original
image to the middle pixel value. The purpose of the median filtering is to
maintain the edge of the image. Then thresholding is carried out to identify
tumors based on gray level distribution. Thresholding results are used as input
to find the largest area. This largest area is useful for separating tumors from
other tissues. Then the brain segmentation is carried out using the watershed
method which begins by marking the brain region and the outer region of the
brain. This marking is useful for distinguishing the brain region and the outer
region of the brain. Watershed give different color in the marked area. After
that, the removal of skull bones with cropping method.

50
 7.1 OUTPUT IMAGES

7.1.1 Input image

This is the first step of our proposed project .In this the data is been provided that
is the magnetic resonance images(MRI) that are been collected in their original
format’s that are (.ima, .dcm). Mostly the mri images are of .dcm (DICOM[13])
Digital imaging and communications in medicine. We have used file operations
fopen(), fclose() available in matlab to read MRI images. Here the gray scale MRI
images are been provided as input to the system.

FIG7.1.1 Input image

51
7.1.2 Preprocessing

The aim of pre-processing is an improvement of the image data that suppresses

unwilling distortions or enhances some image features important for further
processing, although geometric transformations of images (e.g. rotation, scaling,
translation) are classified among pre-processing methods here since similar techniques
are used.

FIG7.1.2 Preprocessing

52
7.1.3 Morphological operation

Morphological image processing is a collection of non-linear operations related to

the shape or morphology of features in an image. Morphological operations rely only
on the relative ordering of pixel values, not on their numerical values,and therefore are
especially suited to the processing of binary images. Morphological operations can
also be applied to greyscale images such that their light transfer functions are
unknown and therefore their absolute pixel values are of no or minor
interest.Morphological techniques probe an image with a small shape or template
called a structuring element.

FIG7.1.3 Morphological operation

53
7.1.4 Discrete wavelet transform(DWT)

We can divide tumors in according to how exponentially they developed i.e. growth
rate, with lower-grade tumors often being begin and higher-grade tumors being
malignant. Based on interpolation of low frequency sub band images obtained by
discrete wavelet transform (DWT) and the input image, the brain tumor detection is
obtained by using Haar wavelet transform. Database image is also decomposed by
using Haar wavelet transform by two levels and this database image is compared with
the input image by using Mutual information principle. Both input image and database
image is decomposed into different sub bands by using DWT.

FIG7.1.4 Discrete wavelet transform

54
7.1.5 Segmentation

Detecting an object from a background, we can break the image up into segments in
which we can do more processing on. This is typically called Segmentation. Brain
tumor segmentation is a brain tumor assisted diagnosis technology that separates
different brain tumor structure. the state-of-the-art algorithms with a full automatic
segmentaion are discussed. Finally, an assessment of the current state is presented

FIG7.1.5.a Segmentation

55
 FIG7.1.5.b Segmentation

7.2 Summary

Brain tumor detection technique is used for developing earlier disease

detection and treatment stages. The tumor area is taken in account to discover
the abnormality of the brain tumor in the target Brain tumor MRI image. The
performance of detecting Brain tumor MRI images is measured in terms of
Sensitivity, Specificity, Accuracy and other parameters. The next chapter
describes about the Conclusion.

56
 CHAPTER 8
CONCLUSION

57
 CHAPTER 8
CONCLUSION

The brain tumor is one of the deadliest diseases in today’s world. So in order to find
the tumor tissues at the earliest stage using the proposed algorithm with the help of
MATLAB tool, the proposed system is developed by analyzing on the previous
system provides an idea over the segmentation and classification and an effective
algorithm is designed using MATLAB. MRI images are best suitable for brain tumor
detection. In this project, Digital Image Processing Techniques are important for brain
tumor detection by MRI images. The preprocessing techniques include different
methods like Filtering, Contrast enhancement, are used for image smoothing. The
preprocessed images are used for post processing operations like; threshold,
histogram, segmentation and morphological operation, which is used to enhance the
images and the type of brain tumor is specified using SVM classifier. So in order to
find the tumor tissues at the earliest stage using the proposed algorithm with the help
of MATLAB tool, the proposed system is developed by analyzing on the previous
system provides an idea over the segmentation and classification and an effective
algorithm is designed using MATLAB.

58
 REFERENCES

[1] Huang Meiyan, Wei Yang, Wu Yao, Jiang Jun, Chen Wufan, and QianjinFeng, “Brain
Tumor Segmentation Based on Local Independent Projection-based Classification”, IEEE
Transactions on Biomedical Engineering, 2019

[2] Ines NJEH, LamiaSallemi, Mohammed Ben Slima, StephaneLehericy. “A Computer

Aided Diagnosis ‘CAD’ for Brain Glioma Exploration”. International Conference on
Advanced Technologies Signal and Image Processing.2018

[3] Eman Abdel-Maksoud*, Mohammad Elmogy, Rashid AlAwadi.”Brain Tumor

Segmentation Based on a Hybrid Clustering Technique”.Egyptian Informatics
Journal.2018

[4] RiyantoSigit, ZainalArief, MochamadMobedBachtiar. ”Development of Healthcare

Kiosk for Checking Heart Health”.EMITTER International Journal of Engineering
Technology.2015

[5] DawnglianaMalsawm, Deb Daizy, HandiqueMousum, and Roy Sudipta, “Automatic

Brain Tumor Segmentation in MRI: Hybridized Multilevel Thresholding and Level Set”,
International Symposium on Advanced Computing and Communication (ISACC). 2015.

[6] PrakashMahindrakar and Dr. M. Hanumanthappa, “Data Mining In Healthcare: A

Survey of Techniques and Algorithms with Its Limitations and Challenges”, Int. Journalof
Engineering Research and Applications, ISSN : 2248-9622, Vol. 3, Issue 6, Nov-Dec
2013, pp.937-941

[7] KailashSinha, G.R.Sinha, “Efficient Segmentation Methods for Tumor Detection in

MRI Images”, 2014 IEEE Student’s Conference on Electrical, Electronics and Computer
Science, 978-1-4799-2526- 1/14/$31.00 ©2014 IEEE
59
[8] R.S.RajKumar and G.Niranjana, “Image Segmentation and Classification of MRI
Brain Tumor Based on Cellular Automata and Neural Networks”, IJREAT International
Journal of Research in Engineering & Advanced Technology, Volume 1, Issue 1, March,
2013 ISSN: 2320 – 8791.

[9] H. B. Nandpuru, Dr. S. S. Salankar, Prof. V. R. Bora, MRI brain cancer classification
using support vector machine. 2014 IEEE Students' Conference on Electrical, Electronics
and Computer Science, 978-1- 4799-2526-1/14/$31.00 ©2014 IEEE

[10] A. Padma and R.Sukanesh, “SVM based classification of soft tissues in brain CT

images using wavelet based dominant gray level run length texture features”, middle-east
journal of scientific research, 2013, 13(7): 883-888

60