Identification of Brain tumor using Image processing technique

CHAPTER 1

INTRODUCTION

Computer-aided diagnostic (CAD) system helps radiologists in detecting and

analyzing Tumors. The ability to turn detection into diagnostics by ranking the areas of
interest detected on a images by probability of malignancy, is a breakthrough in the field of
CAD system. This is important for both physicians and patients because as evaluation
becomes more exact, the number of unnecessary procedures is greatly decreased. A CT Scan
(Computed tomography) is useful for viewing bone structures. MRI is suited for examining
soft tissues. The time taken for CT scans is less than 5 minutes. An MRI, on the other hand,
30 minutes is necessary. MRI scan is a substantial noninvasive medical diagnostic tool that
uses a radiology technique. It is a painless diagnosis and has the advantage of avoiding X-ray
radiation exposure over the CT scan. The image and resolution produced by MRI scan is
quite exhaustive and can detect miniature changes of structures within the body. The images
are originated using super conducting magnets and pulsed radio waves. MRI is more versatile
than the X-ray and is used to determine a large diversity of medical conditions. Automatic
detection and diagnosis is necessary for planning and treatment. Manual segmentation and
classification is time consuming at the same time subject to make error. There are two critical
problem is existing .The first problem is differentiating the abnormal tissue from normal
tissue and second is finding the boundary precisely.

Brain tumor is the major disease which doesn’t have any complete solution. Brain
tumors can be classified into two types. 1. Benign tumors 2. Malignant tumors. Benign brain
tumor cells are growing slowly and having distinct boundaries. They do not spread other
areas in the body. Surgery alone may cure this kind of tumor. The malignant tumor leads to
life threatening. It is made up of cancerous cells can destroy healthy tissue so these areas are
not working properly. Malignant tumors are very dangerous than benign tumors it leads to
cancer. Malignant tumors of the brain affect over 50,000 adults in the country each year and
rate has been rising for the last 50 years. Brain tumors are the second leading cause of cancer
related deaths in children and male. As a brain tumor cells are growing in the back of the

Dept. of ECE AITM, Belagavi Page 1

 Identification of Brain tumor using Image processing technique

brain it can cause vision problems. If it is in the sides of the brain it can cause speech or
movement.

The information housed on the cloud is often seen as valuable to individuals with
malicious intent. There is a lot of personal information and potentially secure data that
people store on their computers, and this information is now being transferred to the cloud.
This makes it critical for you to understand the security measures that your cloud provider
has in place, and it is equally important to take personal precautions to secure your data.

Brain tumor at early stage is very difficult task for doctors to identify. MRI images
are more prone to noise and other environmental interference. So it becomes difficult for
doctors to identify tumor and their causes. So here we come up with the system, where
system will detect brain tumor from images. Here we convert image into grayscale image.
We apply filter to image to remove noise and other environmental interference from image.
User has to select the image. System will process the image by applying image processing
steps. We applied a unique algorithm to detect tumor from brain image. But edges of the
image are not sharp in early stage of brain tumor. So we apply image segmentation on image
to detect edges of the images. In this method we applied image segmentation to detect tumor.
Here we proposed image segmentation process and many image filtering techniques for
accuracy. This system is implemented in mat lab.

Dept. of ECE AITM, Belagavi Page 2

 Identification of Brain tumor using Image processing technique

CHAPTER 2

LITERATURE SURVEY

R. J. Ramteke, KhachaneMonali proposed a method for automatic classification of

medical images in two classes Normal and Abnormal based on image features and automatic
abnormality detection. KNN classifier is used for classifying image. K-Nearest Neighbour
(K-NN) classification technique is the simplest technique conceptually and computationally
that provides good classification accuracy. The K-NN algorithm is based on a distance
function and a voting function in k-Nearest Neighbors, the metric employed is the Euclidean
distance. EM has high approximation capability and much faster convergence. KNN was
chosen for classification purpose after verifying its classification accuracy with SVM.
Normal Classified image displayed as resultant normal image. Abnormal classified image is
passed to the next phase for further processing.

Khushboo Singh, SatyaVerma proposed advanced classification techniques based on

Support Vector Machines (SVM) are proposed and applied to brain image classification
using features derived. SVM is a artificial neural network technique used for supervised
learning of classification. Important characteristics of SVM are its ability to solve
classification problems by means of convex quadratic programming (QP) and also the
sparseness resulting from this QP problem. The learning is based on the principle of
structural risk maximization. Instead of minimizing an objective function based on the
training samples (such as mean square error), the SVM attempts to minimize the bound on
the generalization error (i.e., the error made by the learning machine on the test data not used
during training).

ShwetaJain classifies the type of tumor using Artificial Neural Network (ANN) in
MRI images of different patients with Astrocytoma type of brain tumor. The extraction of
texture features in the detected tumor has been achieved by using Gray Level Co-occurrence
Matrix (GLCM). An artificial neural network (ANN), generally called neural network (NN),
is a mathematical model or computational model that is inspired by the structure and/or
functional aspects of biological neural networks. A neural network contains of an
interconnected group of artificial neurons (processing element), working in unison to solve

Dept. of ECE AITM, Belagavi Page 3

 Identification of Brain tumor using Image processing technique

specific problems. Back Propagation learning algorithm is a supervised learning algorithm.

This learning algorithm is applied to multilayer feed-forward networks consisting of
processing elements (neurons) with continuous differentiable activation functions (Tan-
sigmoid and logsigmoid). The networks associated with back-propagation learning algorithm
are also called back-propagation learning networks (BPNs). For a given set of training input
output pair, this algorithm provides a procedure for changing the weights in a BPN to classify
an input correctly. The concept for this weight update algorithm is basically the gradient-
descent method as used in case of simple preceptor networks with differentiable units. This is
a way where the error is propagated back to hidden unit.

Priyanka, BalwinderSingh focused on survey of well-known brain tumor detection

algorithms that have been proposed so far to detect the location of the tumor. The main
concentration is on those techniques which use image segmentation to detect brain tumor.
Image segmentation is the process of partitioning a digital image into multiple segments. The
goal of segmentation is to simplify and/or change the representation of an image into
something that is more meaningful and easier to analyze. More precisely, image
segmentation is the process of assigning a label to every pixel in an image such that pixels
with the same label share certain visual characteristics. Using segmentation in medical
images is a very important task for detecting the abnormalities, study and tracking progress
of diseases and surgery planning. The segmentation of brain tumor can be done using various
edge detection. Edge based segmentation is the most common method based on detection of
edges i.e. boundaries which separate distinct regions. Edge detection method is based on
marking of discontinuities in gray level, color etc., and often these edges represent
boundaries between objects. This method divides an image on the basis of boundaries.
Numbers of edge detecting operators based on gradient (derivative) function are available.
For brain tumor detection various edge detection operators are used which are sobel edge
detection, prewitt edge detection operator and canny edge detection operator. From the three
methods of edge detection, they found that Sobel method is more suitable for edge detection
of brain tumor. This method has a little mean and standard deviation value. Classifiers such
as K-Nearest Neighbor (KNN), Artificial Neural Network (ANN) etc. are used for various
applications such as hand written digit identification, object identification, speaker
identification, face identification, text classification and for medical applications. Each of the

Dept. of ECE AITM, Belagavi Page 4

 Identification of Brain tumor using Image processing technique

classification schemes previously mentioned has its own unique properties and associated
strengths and problems. In KNN, the major limitation is that it uses all features in distance
computation ally intensive, mainly when the size of training set increases.

Dept. of ECE AITM, Belagavi Page 5

 Identification of Brain tumor using Image processing technique

CHAPTER 3

DIGITAL IMAGE PROCESSING

Digital image processing is a regularly growing and dynamic territory in the field of
connected optics with applications connecting into our ordinary life. Pictures are created by
a large variety of physical gadgets, such as digital cameras and video camera, x-ray gadgets,
microscopes, ultrasound scanning devices etc. These are utilized for different purposes,
including multimedia and entertainment, business and economy, medical imaging,
industries and mechanical devices, military combat, security, and experimental and research
applications. The objective for every situation is for an onlooker, either be human or
mechanical device, to extricate valuable data about the scene being visible. Quite often these
real world images will not be suitable for processing right away, hence they require some
suitable image processing, which are specific to the application in question.

This type of processing and modifications is termed as image enhancement and any
processing involving an onlooker to collect values data from the picture is known as image
analysis. These two techniques sound similar, but they differ from each other in their output
generated and also in methods and procedures involved to accomplish the task. Image
enhancement can be done in various method by using chemicals, optical instruments, and by
any other electronic means. On the other hand, image analysis must be performed
principally by expertise humans or trained technicians and through electronic devices.

Digital image processing is a part of the computer vision in the electronic realm
wherein the images are transformed to a matrices of bounded integers commonly known as
pixels. These pixels represents the characteristics of the in image with their physical
quantity such as scene luminance, color maps etc. and they are stored in the memory in the
same fashion. The computer or other digital processors also perform in the same fashion.

Dept. of ECE AITM, Belagavi Page 6

 Identification of Brain tumor using Image processing technique

3.1 CHARACTERISTICS OF IMAGE PROCESSING:

Before going to processing an image, it is converted into a digital form. Digitization includes
sampling of image and quantization of sampled values. After converting the image into bit
information, processing is performed. This processing technique may be, Image
enhancement, Image restoration, and Image compression.

3.1.1 IMAGE ENHANCEMENT:

It refers to accentuation, or sharpening, of image features such as boundaries, or contrast to

make a graphic display more useful for display & analysis. This process does not increase the
inherent information content in data. It includes gray level & contrast manipulation, noise
reduction, edge crispening and sharpening, filtering, interpolation and magnification, pseudo
coloring, and so on.

3.1.2 IMAGE RESTORATION:

It is concerned with filtering the observed image to minimize the effect of

degradations. Effectiveness of image restoration depends on the extent and accuracy of the
knowledge of degradation process as well as on filter design. Image restoration differs from
image enhancement in that the latter is concerned with more extraction or accentuation of
image features.

3.1.3 IMAGE COMPRESSION:

It is concerned with minimizing the number of bits required to represent an image.

Application of compression are in broadcast TV, remote sensing via satellite, military
communication via aircraft, radar, teleconferencing, facsimile transmission, for educational
& business documents, medical images that arise in computer tomography, magnetic
resonance imaging and digital radiology, motion, pictures, satellite images, weather maps,
geological surveys and so on.

 Text compression – CCITT GROUP3 & GROUP4

 Still image compression – JPEG
 Video image compression - MPEG

Dept. of ECE AITM, Belagavi Page 7

 Identification of Brain tumor using Image processing technique

3.2 COLOR SPACE

A color space is a mathematical model used to represent the colors of an image in
integer values of the constituent color intensities. For every situation, a color space was
chosen for an application as per the necessity and requirement. The set of available colors
can be embodied mathematically for qualitative and quantitative purposes. This
mathematical representation is known as a colorspace. The use different color spaces for
numerous applications gave rise to its development. Ordinarily, a color space characterizes
an image in as low as one dimension, to the larger four dimension model spaces. Each
dimension represents a basic element of color component or a channel.

In a one dimension color space model, each pixel of the image contains some value
of intensity based on the image. This one dimensional colorspace is called as grayscale.
When a color image is split into its ingredient color matrices, then each dimension
representing each color forms a grayscale image.

The images used in image processing comes with various formats like, jpeg, bitmap
images called bmp, tiff, gif etc. These image formats usually extends the rgb colorspace.
The rgb colorspace can be viewed as 3 dimensional cube with each dimension representing
a color, red, blue and green. The origin, where all the 3 coordinates are 0, represents black,
whereas the foremost point where the maximum value of all 3 coordinates intersect, is
white. The other color space also work in the same way. Some of the popular colorspace
models used for various applications are RGB, YCbCr, HSV, Lab, HSI, etc.

Dept. of ECE AITM, Belagavi Page 8

 Identification of Brain tumor using Image processing technique

3.2.1 RGB COLOR SPACE

The RGB is the visible color space of the living world as perceived by humans. The
RGB color space is made up of the three constituents primary colors: red, green and blue.
This color model is used in most pf color crt and few lcd monitors. Since the colors are
added between 2 or 3 base colors in order to make new colors, rgb colorspace is thought of
as the additive primaries. Spectral components of these three colors combine selectively
with variable proportions to produce a new color The RGB color model is represented using
the cartesian coordinate system which implies a 3-dimensionalcube with red, green and blue
at the corners. When a color is extracted from the rgb space, it resembles a grayscale image.
A representation of the rgb color model is shown in figure 4.1. The grayscale of the image is
given by diagonal from origin to extreme.

Fig. 3.1 RGB Color Space

In a cartesian coordinate system, the values of R, G, B ranges from 0 to 255. If the

values of all three color is 0, it results in black. And when all three color are 255, it gives
white.The RGB color space is the most common choice for computer graphics, hence it is
widely accepted as a compliant color space for computer graphics system.

Dept. of ECE AITM, Belagavi Page 9

 Identification of Brain tumor using Image processing technique

3.2.2 YCBCR COLOR SPACE

YCbCr color space has been introduced to meet the increasing demands for digital
algorithms for handling and processing digital image and video information. This model has
since become a broadly accepted model in a digital imaging and video processing. Many
television transmission systems use the family of YCbCr color spaces.

There several variants in the YCbCr. They are YUV and YIQ, to name a few..
YCbCr is the digital color system, and the YUV and YIQ belong to analog spaces used in
video transmission with PAL and NTSC systems. These colorspaces separate Red, Green,
Blue from RGB colorspace into luminance and chrominance information. This makes it
very light and hence they are useful in image and video compression and transmission
applications.

Fig. 3.2 YCBCR Color Space

YCbCr is a digital color system which was first defined by the CCIR (International
Consultative Committee on Broadcasting). It is also known as the CCIR 601 color space.
YCbCr defines color images information in terms of luminance denoted by the Y
component and two different chrominance values. The Cr represents the chrominance of
Red colors and Cb represents the chrominance of Blue colors, unlike combination of the
spectrum like the RGB space. In YCbCr color space, Y said Luminance, and it is also the
image gray value, that is the sense of brightness which caused by color affecting human
eyes; Cb and Cr which are Chrominance, reflects the color sorts, called the blue color and
red color.

Dept. of ECE AITM, Belagavi Page 10

 Identification of Brain tumor using Image processing technique

3.2.3 HSV COLOR SPACE

HSV color space was introduced due to the fact that a color can be represented
without intensity or luminance values. Hence, the hue, saturation and intensity are three
channels that are used to describe a color in this model. In HSV color space, the percentage
of the color is not determined by its intensity as in RGB, instead adjusting the hue will result
in the desired color.

HSV stands for hue, saturation and value. HSV is a cylindrical representation of
RGB. When a cylinder is placed with its axis in vertical direction, the angle about the
central axis is the hue, where each degree of rotation gives a different color.

The saturation is defined by the distance from the center axis. And the distance in
the direction of the center axis is called the value. The bottom most part of the cylinder is
black along all the direction of axis, and the topmost part of cylinder at the center is the
white.

Fig. 3.3 HSV color space

The other varients of HSV are HSL and HIS, HSL means hue, saturation and
lightness, but it is also called HSB by replacing lightness with brightness.

Dept. of ECE AITM, Belagavi Page 11

 Identification of Brain tumor using Image processing technique

3.3 COLOR SPACE CONVERSION

In the classification of food grains, the color extraction is not suitable in RGB color
space. Therefore, there is a need to convert eh given image into other color space. The
YcbCR color space is the first one to be chosen as it provides better threshold for object
detection at lesser design complexity. For SVM and dwt feature extraction, HSV and lab is
more suited. Hence we look at standard procedure to converts between these color space.
The RGB color space is the predominant selection for computer vision because color
displays user red, green and blue to create the desired color as visualized by the human eye.
YcbCr color space is a perception of color and luminance, which are not true readable for
human. Hence they are used in the transmission of video signal as it uses lesser bandwidth
and low space in memory.

Color Space Converters are very much essential in any image processing application
as various algorithms and programs work on images represented in specific color space. The
humans can perceive only RGB color images and images from other color spaces appear
meaningless and distorted. But RGB is not used in all the stages which doesn’t have human
intervention or perception. Many color space conversions are used in video and image
displays, like televisions, computer monitors, color printers and surveillance systems.

Color space conversion is obligatory for conveying the multimedia data between
devices that use distinctive color space models. The colorspace is 3 dimensional space and
all the color space models have 3 dimension. Hence the color conversion involves the values
being mapped from one dimension of a source color model to the correlating one in the
resulting color model.

Dept. of ECE AITM, Belagavi Page 12

 Identification of Brain tumor using Image processing technique

CHAPTER 4

SYSTEM DESIGN & METHODOLOGY

EM TECHNIQUE WATERSHED TECHNIQUE

Input Brain MRI Input Brain MRI
(Acquisition) (Acquisition)

Preprocessing
Gray Scale Image
(Applying Filters)

Image Enhancement Sharpened Image

Feature Extraction
Enhanced Image

Segmentation
Threshold Segmentation

Watershed
Algorithm Evaluation
Segmentation
(EM & SD)

Segmented MRI Output Image

Combine the Output

Output Image with Tumor Portion Highlighted

Fig. 4.1 System design & Methodology

Dept. of ECE AITM, Belagavi Page 13

 Identification of Brain tumor using Image processing technique

Our easy and effective EM method can be divided in seven steps:

INPUTS : MRI IMAGES

OUTPUTS : BINARIZES MRI OF BRAIN IMAGES INDICATING TUMOR PORTION.

STEP 1:Take an M RI image I(x,y).

STEP 2: If it is color image then convert it int o gray scale i mage Ig(x,y).

STEP 3: Calculate standard deviation of the image and store the intensity value in TS.

STEP 4: Calculate the threshold value by production of standard deviation and a predefine
constant H, i.e. Threshold intensity value T= TS*H.

STEP 5: Scan left to right and top to bottom, each pixel of the gray image Ig(x,y).

STEP 6:Find a binary image IB from the gray image lg(x,y) in the following way,
IB(x,y) = 1 lg(x,y) >= T
IB(x,y) = 0 lg(x,y) < T

STEP 7: IB is the output binary image.

Dept. of ECE AITM, Belagavi Page 14

 Identification of Brain tumor using Image processing technique

Our easy and effective Watershed technique can be divided in seven steps:

INPUTS : MRI IMAGES

OUTPUTS : BINARIZES MRI OF BRAIN IMAGES INDICATING TUMOR PORTION.

STEP 1:Take an M RI image I(x,y).

STEP 2: If it is color image then convert it int o gray scale i mage Ig(x,y).

STEP 3: Then the image must be sharpened and enhanced as mentioned in algorithm.

STEP 4: Calculate the threshold value by production of standard deviation and a predefine
constant H, i.e. Threshold intensity value T= TS*H.

STEP 5: Scan left to right and top to bottom, each pixel of the gray image Ig(x,y).

STEP 6: The watershed transform decomposes an image completely and thus assigns each
pixel either to a region or watershed.

STEP 7: IB is the output binary image.

Dept. of ECE AITM, Belagavi Page 15

 Identification of Brain tumor using Image processing technique

CHAPTER 5
SOFTWARE IMPLEMENTATION
5.1 MATLAB
Using MATLAB, a basic image analysis GUI will develop to provide the end-users
with options to segment and detect the tumor. The output will display the final processed
image and the region of tumor that the GUI can detect. The GUI comprises of a several sets
of buttons to execute different functions and output fields to display the result. The first set of
buttons serves as functions to load an original image, save or reset a processed image and
reset or close the GUI.

Our selection of MATLAB as the platform for image processing is due to the flexible
and manageable environment in terms of syntax and a large library of in-built functions.
Image processing offers two advantages over traditional manual methods of analysis: 1)
Human vision, while highly sensitive, can be easily biased by pre-conceived notions of
objects and concepts; automated image analysis provides an unbiased approach to extracting
information from image data and testing hypotheses. 2) Once an image-analysis routine is
devised, it can be applied to a large number of microscopy images, facilitating the collection
of large amounts of data for statistical analysis.

Moreover, the Image Processing Toolbox provides a comprehensive set of reference-standard

algorithms, functions and apps for image processing, analysis, visualization, and algorithm
development.

5.2 IMAGE REPRESENTATION IN MATLAB

MATLAB handles images as matrices. This involves breaking each pixel of an image
down into the elements of a matrix. MATLAB distinguishes between color and grayscale
images and therefore their resulting image matrices differ slightly. A color is a composite of
some basic colors. MATLAB therefore breaks each individual pixel of a color image (termed
‘true color’) down into Red, Green and Blue values. What we get as a result, for the entire

Dept. of ECE AITM, Belagavi Page 16

 Identification of Brain tumor using Image processing technique

image, are 3 matrices, one representing each color. The three matrices are stacked next to
each other creating a 3 dimensional m by n by 3 matrixes.
For an image which has a height of 5 pixels and width of 10 pixels the resulting in
MATLAB would be a 5 by 10 by 3 matrixes for a true color image.

Fig. 5.1 Color image representation and RGB matrix

Dept. of ECE AITM, Belagavi Page 17

 Identification of Brain tumor using Image processing technique

A grayscale image is a mixture of black and white colors. These colors, or as some may
term as ‘shades’, are not composed of Red, Green or Blue colors. But instead they contain
various increments of colors between white and black. Therefore to represent this one range,
only one color channel is needed. Thus we only need a 2 dimensional matrix, m by n by 1.
MATLAB terms this type of matrix as an Intensity Matrix, because the values of such a
matrix represent intensities of one color.For an image which as height of 5 pixels and width
of 10 pixels the resulting matrix would be a 5 by 10 matrix for grayscale image.

Fig. 5.2 Grayscale image representation

5.3 OVERVIEW OF MATLAB

Dept. of ECE AITM, Belagavi Page 18
 Identification of Brain tumor using Image processing technique

MATLAB is a high-performance language for technical computing. It integrates

computation, visualization, and programming in an easy-to-use environment where problems
and solutions are expressed in familiar mathematical notation.

Fig. 5.3 MATLAB R2015a

Typical uses include

• Math and computation

• Algorithm development

• Data acquisition

• Modeling, simulation, and prototyping

• Data analysis, exploration, and visualization

• Scientific and engineering graphics

• Application development, including graphical user interface building

Dept. of ECE AITM, Belagavi Page 19

 Identification of Brain tumor using Image processing technique

MATLAB is an interactive system whose basic data element is an array that does not
require dimensioning. This allows you to solve many technical computing problems,
especially those with matrix and vector formulations, in a fraction of the time it would take to
write a program in a scalar non interactive language such as C or Fortran. The name
MATLAB stands for matrix laboratory. MATLAB was originally written to provide easy
access to matrix software developed by the LINPACK and EISPACK projects. Today,
MATLAB engines incorporate the LAPACK and BLAS libraries, embedding the state of the
art in software for matrix computation.

MATLAB has evolved over a period of years with input from many users. In
university environments, it is the standard instructional tool for introductory and advanced
courses in mathematics, engineering, and science. In industry, MATLAB is the tool of choice
for high-productivity research, development, and analysis.

MATLAB features a family of add-on application-specific solutions called toolboxes.

Very important to most users of MATLAB, toolboxes allow you to learn and apply
specialized technology. Toolboxes are comprehensive collections of MATLAB functions
(M-files) that extend the MATLAB environment to solve particular classes of problems.
Areas in which toolboxes are available include signal processing, control systems, neural
networks, fuzzy logic, wavelets, simulation, and many others. The MATLAB System

The MATLAB system consists of these main parts:

5.3.1 DESKTOP TOOLS AND DEVELOPMENT ENVIRONMENT

This is the set of tools and facilities that help you use MATLAB functions and files.
Many of these tools are graphical user interfaces. It includes the MATLAB desktop and
Command Window, a command history, an editor and debugger, a code analyzer and other
reports, and browsers for viewing help, the workspace, files, and the search path.

5.3.2 MATLAB MATHEMATICAL FUNCTION LIBRARY

Dept. of ECE AITM, Belagavi Page 20

 Identification of Brain tumor using Image processing technique

This is a vast collection of computational algorithms ranging from elementary

functions, like sum, sine, cosine, and complex arithmetic, to more sophisticated functions
like matrix inverse, matrix eigenvalues, Bessel functions, and fast Fourier transforms.

5.3.3 MATLAB LANGUAGE

This is a high-level matrix/array language with control flow statements, functions,

data structures, input/output, and object-oriented programming features. It allows both
“programming in the small” to rapidly create quick and dirty throw-away programs, and
“programming in the large” to create large and complex application programs.

5.3.4 GRAPHICS

MATLAB has extensive facilities for displaying vectors and matrices as graphs, as
well as annotating and printing these graphs. It includes high-level functions for two-
dimensional and three-dimensional data visualization, image processing, animation, and
presentation graphics. It also includes low-level functions that allow you to fully customize
the appearance of graphics as well as to build complete graphical user interfaces on the
MATLAB applications.

5.3.5 MATLAB EXTERNAL INTERFACES

This is a library that allows you to write C and Fortran programs that interact with
MATLAB. It includes facilities for calling routines from MATLAB (dynamic linking),
calling MATLAB as a computational engine, and for reading and writing MAT-files.

5.3.6 IMAGE PROCESSING TOOLBOX

Image Processing Toolbox provides a comprehensive set of reference-standard

algorithms and graphical tools for image processing, analysis, visualization, and algorithm
development. You can perform image enhancement, image deblurring, feature detection,
noise reduction, image segmentation, spatial transformations, and image registration. Many

Dept. of ECE AITM, Belagavi Page 21

 Identification of Brain tumor using Image processing technique

functions in the toolbox are multithreaded to take advantage of multicore and multiprocessor
computers.

Image Processing Toolbox supports a diverse set of image types, including high
dynamic range, gigapixel resolution, ICC-compliant color, and tomographic images.
Graphical tools let you explore an image, examine a region of pixels, adjust the contrast,
create contours or histograms, and manipulate regions of interest (ROIs). With the toolbox
algorithms you can restore degraded images, detect and measure features, analyze shapes and
textures, and adjust the color balance of images.

KEY FEATURES

 Image enhancement, filtering, and deblurring. Image analysis, including

segmentation, morphology, feature extraction, and measurement
 Spatial transformations and image registration
 Image transforms, including FFT, DCT, Radon, and fan-beam projection
 Workflows for processing, displaying, and navigating arbitrarily large images
 Modular interactive tools, including ROI selections, histograms, and distance
measurements
 ICC color management
 Multidimensional image processing
 Image-sequence and video display
 DICOM import and export

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

Dept. of ECE AITM, Belagavi Page 22

 Identification of Brain tumor using Image processing technique

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

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 for example.
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 the DICOM file format, including associated metadata, as well as
the Analyze 7.5 and Interfile formats. The toolbox can also read geospatial images in the
NITF format and high dynamic range images in the HDR format.

5.3.8 DISPLAYING AND EXPLORING IMAGES

Image Processing Toolbox extends MATLAB graphics to provide image display

capabilities that are highly customizable. You can create displays with multiple images in a
single window, annotate displays with text and graphics, and create specialized displays such
as histograms, profiles, and contour plots.

In addition to display functions, the toolbox provides a suite of interactive tools for
exploring images and building GUIs. You can view image information, zoom and pan around
the image, and closely examine a region of pixels. You can interactively place and
manipulate ROIs, including points, lines, rectangles, polygons, ellipses, and freehand shapes.
You can also interactively crop, adjust the contrast, and measure distances. The suite of tools
is available within Image Tool or from individual functions that can be used to create
customized GUIs.

Dept. of ECE AITM, Belagavi Page 23

 Identification of Brain tumor using Image processing technique

The toolbox includes tools for displaying video and sequences in either a time-lapsed
video viewer or an image montage. Volume visualization tools in MATLAB let you create is
of surface displays of multidimensional image data sets.

5.3.9 PREPROCESSING AND POSTPROCESSING 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.

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 decorrelation 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.

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,

Dept. of ECE AITM, Belagavi Page 24

 Identification of Brain tumor using Image processing technique

atmospheric conditions, short exposure time, and other factors. All deblurring functions work
with multidimensional images.

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.

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

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.

Dept. of ECE AITM, Belagavi Page 25

 Identification of Brain tumor using Image processing technique

5.3.10 ANALYZING IMAGES

Image Processing Toolbox provides a comprehensive suite of reference-standard

algorithms and graphical tools for image analysis tasks such as statistical analysis, feature
extraction, and property measurement.

Statistical functions let you analyze the general characteristics of an image by:

 Computing the mean or standard deviation

 Determining the intensity values along a line segment
 Displaying an image histogram
 Plotting a profile of intensity value

Edge-detection algorithms let you identify object boundaries in an image. These

algorithms include the Sobel, Prewitt, Roberts, Canny, and Laplacian of Gaussian methods.
The powerful Canny method can detect true weak edges without being “fooled” by noise.

Image segmentation algorithms determine region boundaries in an image. You can

explore many different approaches to image segmentation, including automatic thresholding,
edge-based methods, and morphology-based methods such as the watershed transform, often
used to segment touching objects.

Morphological operators enable you to detect edges, enhance contrast, remove noise,
segment an image into regions, thin regions, or perform skeletonization on regions.
Morphological functions in Image Processing Toolbox include:

 Erosion and dilation

 Opening and closing
 Labeling of connected components
 Watershed segmentation
 Reconstruction
 Distance transform

Dept. of ECE AITM, Belagavi Page 26

 Identification of Brain tumor using Image processing technique

Image Processing Toolbox also contains advanced image analysis functions that let
you:

 Measure the properties of a specified image region, such as the area, center of mass,
and bounding box
 Detect lines and extract line segments from an image using the Hough transform
 Measure properties, such as surface roughness or color variation, using texture
analysis functions

5.3.11 WORKING WITH LARGE IMAGES

Some images are so large that they are difficult to process and display with standard
methods. Image Processing Toolbox provides specific workflows for working with larger
images than otherwise possible. Without loading a large image entirely into memory, you can
create a reduced-resolution data set (R-Set) that divides an image into spatial tiles and
resamples the image at different resolution levels. This workflow improves performance in
image display and navigation.

Dept. of ECE AITM, Belagavi Page 27

 Identification of Brain tumor using Image processing technique

5.4 DAEMON TOOLS LITE 10

Fig. 5.4 DAEMON Tools Lite 10

DAEMON Tools Lite 10 enables you to emulate up to 4 DT, SCSI or HDD devices.
With Quick Mount option, you do not need to add virtual drives before mounting. Choose an
image, and DAEMON Tools Lite 10 will do the job for you. New virtual drive will be
created in a moment, so an image appears to the system like a real disc. Looks pretty fast and
easy, doesn’t it? This is how DAEMON Tools Lite 10 works.

Dept. of ECE AITM, Belagavi Page 28

 Identification of Brain tumor using Image processing technique

Smart tool to create, organize and mount images

Need to backup some discs? Want to compress an image file to save space on the hard drive
or protect sensitive data with a password? With DAEMON Tools Lite 10, it’s as easy as pie.
Both created and downloaded images are stored in the well-organized Images catalog and are
always at hand. You don’t need to add new images to your collection — just use Scan button
to search for image files on the PC.

The most personal imaging software yet

Must-gave imaging tools are free for personal usage. Want to get more? Choose from 8
advanced feature packs or buy them all with a discount.

Compact and easy-to-use tool to create, store and mount images and emulate virtual drives.
This well-known imaging software combines basic emulation features with advanced
functionality to mount and create virtual hard drives, burn discs and work with iSCSI
Targets.

Dept. of ECE AITM, Belagavi Page 29

 Identification of Brain tumor using Image processing technique

CHAPTER 6

TOOL BOXES AVAILABLE IN MATLAB:

6.1 COMMUNICATIONS TOOLBOX

Communications Toolbox extends the MATLAB technical computing environment with

functions, plots, and a graphical user interface for exploring, designing, analyzing, and
simulating algorithms for the physical layer of communication systems. The toolbox helps
you create algorithms for commercial and defense wireless or wireline systems. The key
features of the toolbox are Functions for designing the physical layer of communications
links, including source coding, channel coding, interleaving, modulation, channel models,
and equalization Plots such as eye diagrams and constellations for visualizing
communications signals Graphical user interface for comparing the bit error rate of your
system with a wide variety of proven analytical results Galois field data type for building
communications algorithms.

6.2 CONTROL SYSTEM TOOLBOX

Complex arithmetic, eigen values, root-finding, matrix inversion, and fast Fourier
transforms are just a few examples of important numerical tools found in MATLAB. More
generally, the MATLAB linear algebra, matrix computation, and numerical analysis
capabilities provide a reliable foundation for control system engineering as well as many
other disciplines. Control System Toolbox builds on the foundations of MATLAB to provide
functions designed for control engineering. Control System Toolbox is a collection of
algorithms, written mostly as M-files, that implements common control system design,

Dept. of ECE AITM, Belagavi Page 30

 Identification of Brain tumor using Image processing technique

analysis, and modeling techniques. Convenient graphical user interfaces (GUIs) simplify
typical control engineering tasks. Control systems can be modeled as transfer functions, in
zero-pole-gain or state-space form, allowing you to use both classical and modern control
techniques. Both continuous-time and discrete-time systems can be manipulated.

Conversions between various model representations are provided. Time responses,

frequency responses, and root loci can be computed and graphed. Other functions allow pole
placement, optimal control, and estimation. Finally, Control System Toolbox is open and
extensible. You can create custom M-files to suit your particular application.

6.3 DATA ACQUISITION TOOLBOX

Data Acquisition Toolbox is a collection of M-file functions and a MEX-file(shared

library) built on the MATLAB® technical computing environment. The toolbox also
includes several dynamic link libraries (DLLs) called adaptors, which enable you to interface
with specific hardware. The toolbox provides you with these main features: A framework for
bringing live, measured data into MATLAB using PC-compatible, plug-in data acquisition
hardware Support for analog input (AI), analog output (AO), and digital I/O (DIO)
subsystems including simultaneous analog I/O conversions Support for these popular
hardware vendors/devices: Advantech boards that use the Advantech Device Manager
Agilent Technologies E1432A/33A/34A VXI modules Keithley boards that use Driver LINX
drivers Measurement Computing Corporation (Computer Boards) boards National
Instruments boards that use Traditional NI-DAQ or NI-DA Qmx software (except
SCXI)Parallel ports LPT1-LPT3Windows sound cards Addiionally, you can use the Data
Acquisition Toolbox Adaptor Kit to interface unsupported hardware devices to the toolbox.
Event-driven acquisitions

6.4 FILTER DESIGN TOOLBOX

Filter Design HDL Coder accelerates the development of application-specific integrated

circuit (ASIC) and field programmable gate array (FPGA) designs and bridges the gap
between system-level design and hardware development by generating hardware description
language (HDL) code based on filters developed in MATLAB®. Currently, system designers
and hardware developers use HDLs, such as very high speed integrated circuit (VHSIC)
Dept. of ECE AITM, Belagavi Page 31
 Identification of Brain tumor using Image processing technique

hardware description language (VHDL) and Verilog, to develop hardware designs. Although
HDLs provide a proven method for hardware design, the task of coding filter designs, and
hardware designs in general, is labor intensive and the use of these languages for algorithm
and system-level design is not optimal.Using Filter Design HDL Coder, system architects
and designers can spend more time on fine-tuning algorithms and models through rapid
prototyping and experimentation and less time on HDL coding. Architects and designers can
efficiently design, analyze, simulate, and transfer system designs to hardware developers.

6.5 FINANCIAL DERIVATIVES TOOLBOX

Financial Derivatives Toolbox provides components for analyzing individual derivative

instruments and portfolios containing several types of interest-rate-based and equity-based
financial instruments. Interest-Rate-Based Derivatives Equity Derivatives

6.6 FINANCIAL TOOLBOX

MATLAB and Financial Toolbox provide a complete integrated computing environment

for financial analysis and engineering. The toolbox has everything that is needed to perform
mathematical and statistical analysis of financial data and display the results with
presentation-quality graphics. You can quickly ask, visualize, and answer complicated
questions.

6.7 FUZZY LOGIC TOOLBOX

Fuzzy Logic Toolbox is a collection of functions built on the MATLAB® numeric

computing environment. It provides tools for you to create and edit fuzzy inference systems
within the framework of MATLAB, or if you prefer, you can integrate your fuzzy systems
into simulations with Simulation link.

6.8 INSTRUMENT CONTROL TOOLBOX

Instrument Control Toolbox is a collection of M-file functions built on the MATLAB®

technical computing environment. The toolbox provides you with these features: A
framework for communicating with instruments that support the GPIB interface (IEEE-488),
the VISA standard, and the TCP/IP and UDP protocols, Note that the toolbox extends the

Dept. of ECE AITM, Belagavi Page 32

 Identification of Brain tumor using Image processing technique

basic serial port features included with MATLAB. Support for IVI, VXI plug &play, and
MATLAB instrument drivers Functions for transferring data between MATLAB and your
instrument: the data can be binary (numerical) or text. The transfer can be synchronous and
block the MATLAB command line, or asynchronous and allow access to the MATLAB
command line. Event-based communication Functions for recording data and event
information to a text file Tools that facilitate instrument control in an easy-to-use graphical
environment

6.9 MAPPING TOOLBOX

Mapping Toolbox provides a comprehensive set of functions and for building map
displays and performing geospatial data analysis in MATLAB. You can create map displays
that combine data from multiple modalities and display them in their correct spatial
relationships. The toolbox supports standard analyses, such as line-of-sight calculations on
terrain data or geographic computations that account for the curvature of the Earth's surface.
Most of the functions in Mapping Toolbox are written in the open MATLAB language. This
means that you can inspect the algorithms, modify the source code, create your own custom
functions, and automate frequently performed tasks.The toolbox supports key mapping and
geospatial data analysis, manipulation, and visualization tasks that are useful in applications
such as earth and planetary scientific research, oil and gas exploration, environmental
monitoring, insurance risk management, aerospace, defense, and security.

6.10 MODEL PREDICTIVE CONTROL

Model Predictive Control Toolbox is a collection of software that helps you design,
analyze, and implement an advanced industrial automation algorithm. Like other ATLAB®
tools, it provides a convenient graphical user interface (GUI) as well as a flexible command
syntax that supports customization. A Model Predictive Control Toolbox controller
automates a target system (the plant) by combining a prediction and a control strategy. An
approximate plant model provides the prediction. The control strategy compares predicted
plant signals to a set of objectives, then adjusts available actuators to achieve the objectives
while respecting the plant's constraints. The controller's constraint-tolerance differentiates it
from other optimal control strategies (e.g., the Linear-Quadratic-Gaussian approach

Dept. of ECE AITM, Belagavi Page 33

 Identification of Brain tumor using Image processing technique

supported in Control System Toolbox). The impetus for this is industrial experience
suggesting that the drive for profitability often pushes the plant to one or more constraints.
The Model Predictive Control Toolbox controller considers such factors explicitly, allowing
it to allocate the available plant resources intelligently as the system evolves over time.

Model Predictive Control Toolbox uses the same powerful linear dynamic modeling
tools found in Control System Toolbox and System Identification Toolbox.

6.11 NEURAL NETWORK TOOLBOX

Neural networks are composed of simple elements operating in parallel. These elements
are inspired by biological nervous systems. As in nature, the network function is determined
largely by the connections between elements. You can train a neural network to perform a
particular function by adjusting the values of the connections (weights) between elements.
Commonly neural networks are adjusted, or trained, so that particular input leads to a
specific target output. Such a situation is shown below. There, the network is adjusted, based
on a comparison of the output and the target, until the network output matches the target.
Typically many such input/target pairs are needed to train a network. Today neural networks
can be trained to solve problems that are difficult for conventional computers or human
beings. Throughout the toolbox emphasis is placed on neural network paradigms that build
up to or are themselves used in engineering, financial, and other practical applications.

6.12 OPTIMIZATION TOOLBOX

Optimization Toolbox extends the capability of the MATLAB® numeric computing

environment. The toolbox includes routines for many types of optimization including
Unconstrained nonlinear minimization Constrained nonlinear minimization, including goal
attainment problems, minimax problems, and semi-infinite minimization problems Quadratic
and linear programming Nonlinear least-squares and curve fitting Nonlinear system of
equation solving Constrained linear least squares Sparse and structured large-scale problems

6.13 PARTIAL DIFFERENTIAL EQUATION

The objectives of Partial Differential Equation Toolbox are to provide you with tools that
define a PDE problem, e.g., define 2-D regions, boundary conditions, and PDE coefficients.
Dept. of ECE AITM, Belagavi Page 34
 Identification of Brain tumor using Image processing technique

Numerically solve the PDE problem, e.g., generate unstructured meshes, discretize the
equations, and produce an approximation to the solution. Visualize the results.

6.14 ROBUST CONTROL TOOLBOX

Robust Control Toolbox is a collection of functions and tools that help to analyze and
design multiinput-multioutput (MIMO) control systems with uncertain elements. uncertain
LTI system models containing uncertain parameters and uncertain dynamics are given.
Analyze tools for MIMO system stability margins and worst case performance are
given.Robust Control Toolbox includes a selection of control synthesis tools that compute
controllers that optimize worst-case performance and identify worst-case parameter values.
The toolbox simplify and reduce the order of complex models with model reduction tools
that minimize additive and multiplicative error bounds. It provides tools for implementing
advanced robust control methods like H, H2, linear matrix inequalities (LMI), and µ-
synthesis robust control. It can shape MIMO system frequency responses and design
uncertainty tolerant controllers.

6.15 SIGNAL PROCESSING TOOLBOX

Signal Processing Toolbox is a collection of tools based on the MATLAB® numeric

computing environment. The toolbox supports a wide range of signal processing operations,
from waveform generation to filter design and implementation, parametric modeling, and
spectral analysis. The toolbox provides two categories of tools, command-line functions and
graphical user interfaces: Command-line functions are available in the following categories:
Discrete-time filter design, analysis, and implementation Analog filter design, analysis, and
implementation Linear system transformations Windows Spectral analysis and cepstral
analysis. A suite of interactive graphical user interfaces are available for Filter design and
analysis Window design and analysis Signal plotting and analysis, spectral analysis, and
filtering.

6.16 SPLINE TOOLBOX

Dept. of ECE AITM, Belagavi Page 35

 Identification of Brain tumor using Image processing technique

This toolbox contains MATLAB versions of the essential programs of the B-spline
package (extended to handle also vector-valued splines) as described in A Practical Guide to
Splines, (Applied Math. Sciences Vol. 27, Springer Verlag, New York (1978), xxiv + 392p;
revised edition (2001), xviii+346p), hereafter referred to as PGS. The toolbox makes it easy
to create and work with piecewise-polynomial functions.

The typical use envisioned for this toolbox involves the construction and subsequent use
of a piecewise-polynomial approximation. This construction would involve data fitting, but
there is a wide range of possible data that could be fit. In the simplest situation, one is given
points and is looking for a piecewise-polynomial function that satisfies , all , more or less.
An exact fit would involve interpolation, an approximate fit might involve least-squares
approximation or the smoothing spline. But the function to be approximated may also be
described in more implicit ways, for example as the solution of a differential or integral
equation. In such a case, the data would be of the form , with A some differential or integral
operator. On the other hand, one might want to construct a spline curve whose exact location
is less important than is its overall shape. Finally, in all of this, one might be looking for
functions of more than one variable, such as tensor product splines.

6.17 STATISTICS TOOLBOX

Statistics Toolbox extends MATLAB to support a wide range of common statistical

tasks. The toolbox contains two categories of tools:Building-block statistical functions for
use in MATLAB programmingGraphical user interfaces (GUIs) for interactive use of the
functionsCode for the building-block functions is open and extensible. It gives MATLAB
Editor to review, copy, and edit the M-file code for any function. It extends the toolbox by
copying code to new M-files or by writing M-files that call toolbox functions.

6.18 SYMBOLIC MATH TOOLBOX

Symbolic Math Toolboxes incorporate symbolic computation into the numeric

environment of MATLAB. These toolboxes supplement MATLAB numeric and graphical
facilities with several other types of mathematical computation such as Calculus, Linear
Algebra, Simplification, Solution of Equations, Special Mathematical Functions, Variable-
Precision Arithmetic, Transforms.
Dept. of ECE AITM, Belagavi Page 36
 Identification of Brain tumor using Image processing technique

There are two toolboxes: The basic Symbolic Math Toolbox is a collection of more than
100 MATLAB functions that provide access to the Maple kernel using a syntax and style
that is a natural extension of the MATLAB language. The basic toolbox also allows to access
functions in the Maple linear algebra package. Extended Symbolic Math Toolbox augments
this functionality to include access to all nongraphics Maple packages, Maple programming
features, and user-defined procedures. With both toolboxes, one can write own M-files to
access Maple functions and the Maple workspace.

6.19 SYSTEM IDENTIFICATION TOOLBOX

System Identification Toolbox extends the MATLAB® computation environment and

lets you fit linear and nonlinear mathematical models to input and output data from dynamic
systems.System identification is especially useful for modeling systems that you cannot
easily represent in terms of first principles. Examples of such complex dynamic systems
include engine subsystems, flight dynamics systems, thermofluid processes, and
electromechanical systems. For real-time applications in adaptive control, adaptive filtering,
or adaptive prediction, one can use System Identification Toolbox to perform recursive
parameter estimation. System Identification Toolbox supports both time- and frequency-
domain data with single or multiple inputs and single or multiple outputs. Time-domain data
can be real or complex. One can also use this Toolbox to estimate models for time-series
data. System Identification Toolbox provides an interactive graphical user interface (GUI)
called the System Identification Tool, which is ideal for getting started with this software.
Alternatively, one can use System Identification Toolbox objects, methods, and functions in
the MATLAB Command Window.

6.20 WAVELET TOOLBOX

Everywhere around us are signals that can be analyzed. For example, there are seismic
tremors, human speech, engine vibrations, medical images, financial data, music, and many
other types of signals. Wavelet analysis is a new and promising set of tools and techniques
for analyzing these signals.

Dept. of ECE AITM, Belagavi Page 37

 Identification of Brain tumor using Image processing technique

Wavelet Toolbox is a collection of functions built on the MATLAB® Technical

Computing Environment. It provides tools for the analysis and synthesis of signals and
images, and tools for statistical applications.

CHAPTER 7

ADVANTAGES AND DISADVANTAGES

7.1 ADVANTAGES

 The processing of images is faster and more cost-effective. One needs less time for
processing, as well as less film and other photographing equipment.

 It is more ecological to process images. No processing or fixing chemicals are needed

to take and process digital images. However, printing inks are essential when printing
digital images.

 Copying a digital image is easy, and the quality of the image stays good unless it is
compressed. For instance, saving an image as jpg format compresses the image. By
resaving the image as jpg format, the compressed image will be recompressed, and
the quality of the image will get worse with every saving.

 Fixing and retouching of images has become easier. In new Photoshop 7, it is possible
to smoother face wrinkles with a new Healing Brush Tool in a couple of seconds.

 The expensive reproduction (compared with rastering the image with a repro camera)
is faster and cheaper.

Dept. of ECE AITM, Belagavi Page 38

 Identification of Brain tumor using Image processing technique

 By changing the image format and resolution, the image can be used in a number of
media.

7.2 DISADVANTAGES

 Misuse of copyright is now easier than it earlier was. For instance, images can be
copied from the Internet just by clicking the mouse a couple of times.

 The value of the image will get worse? This has not necessarily happened
everywhere. Images held in image banks still have reasonably good prices, inspite of
the fact that downloading images through the net is fast and easy.

 The profitableness of digital photography has increased the number of images and
photography in general. ƒ Old professions (such as maker-up, repro cameraman)
vanish, and new ones do not necessarily appear. For instance in mid-1990s, the
newspaper Aamulehti started using computerized make-up, and the traditional
makers-up were left unemployed.

 Work has become more technical, which may not be a disadvantage for everyone. ƒ A
digital file of a certain size cannot be enlarged with a good quality anymore. For
instance, a good poster cannot be made of an image file of 500 kb. However, it is
easy to make an image smaller.

Dept. of ECE AITM, Belagavi Page 39

 Identification of Brain tumor using Image processing technique

RESULT

1. EM ALGORITHM

Fig. EM Algorithm

In this algorithm first we take input as brain tumor affected MRI image. Then after
the prior step we resize the image and convert the image into gray scale so that the value of
each pixel is a single sample representing only an amount of light i.e. it carries only intensity
information. The further step is image filtering which includes the smoothing, sharpening,
removing noise and edge detection. In image segmentation the digital image is divided into

Dept. of ECE AITM, Belagavi Page 40

 Identification of Brain tumor using Image processing technique

multiple segments. The result of image segmentation is a set of segments that collectively
covers the entire image, or a set of contours extracted from the image. Later we have to save
the data for further process and we obtain the output image highlighting the tumor portion as
shown in the fig above.

2. WATERSHED ALGORITHM

Fig. Watershed Algorithm

In this algorithm first we take input as brain tumor affected MRI image. The further
step is image filtering which includes the smoothing, sharpening, removing noise and edge
detection. In image segmentation the digital image is divided into multiple segments. One
aim of this work is to show how the use of mathematical morphology operators can be very
useful in image segmentation. Particularly, we show how the watershed transformation
contributes to improve the numerical results for image segmentation problems.
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

Dept. of ECE AITM, Belagavi Page 41

 Identification of Brain tumor using Image processing technique

the processing of binary images. Morphological operations can also be applied to grayscale
images such that their light transfer functions are unknown and therefore their absolute pixel
values are of no or minor interest. Later we have to save the data for further process and we
obtain the output image highlighting the tumor portion as shown in the fig above.

3. COMBINED RESULT

Fig. Combined result

By using the two algorithms i.e. the EM algorithm and the Watershed algorithm we
get the required result as per the respective algorithms. After combining the two algorithms
we get the accurate and precise result after performing accuracy analysis as shown in the fig
above.

Dept. of ECE AITM, Belagavi Page 42

 Identification of Brain tumor using Image processing technique

CONCLUSION

In medical decision, the use of computer science plays an important role for analyzing
various diseases. Magnetic resonance image (MRI) is a critical part in many researches. So
the MRI brain image is used to implement the system. And morphological operation is used
to detect the tumor region. It is easy to implement and reasonably fast. In this work, the brain
image testing process has been done. This method is given the reliable result for the brain
image. If the brain image has the tumor region, the further processing steps are needed to be
done. The preprocessing step is important to segment the brain image.

After the preprocessing, the brain image is free from noise and this smoothed image
is ready to be used in further processing. In this system, a skull stripping based on threshold
value has been done. This method is able to remove the skull tissues from the brain image
and give the suitable result. And then, marker controlled watershed segmentation has been
done. Therefore, the intensity of normal brain tissues and that of tumor region is split up into
groups. After segmentation, this resulted image is divided into the normal brain region and
the tumor region to get the final segmentation map. After that, the tumor region is detected
from the final segmentation map using morphological operation.

Dept. of ECE AITM, Belagavi Page 43

 Identification of Brain tumor using Image processing technique

REFERENCES

[1]. Skull Stripping of MRI Head Scans based on Chan-Vese Active Contour Model, [Online
Available], www.med.harvad.edu/AANLIB/home.html, accessed on 8 August 2013.

[2]. Magnetic Resonance Image, [Online Available], www.CEwebsource.com, accessed on

18 June 2013.

[3]. Pratik P. Singhai, Siddharth A. Ladhake, “Brain Tumor Detection using Marker Based
Watershed Segmentation from Digital MR images”, International Journal of Innovative
Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-2, Issue-5, April
2013.

[4]. A.Jeeviitha, P. Narendran, “BTS (Brain Tumor Segmentation) Based on Otus

Thresholding,” Indian Journal of Research, Volume:2, Issue:2, ISSN- 2250-1991, February
2013.

[5]. Manor K Kowari and Sourabh Yadav, “Brain Tumor Detection and Segmentation using
Histogram Thresholding”, International Journal of Engineering and Advanced Technology
(IJEAT) ISSN: 2249-898, Volume-1, Issue-4, Journal, India, April 2012.

[6] Swe Zin Oo1, Aung Soe Khaing,“Brain Tumor Detection And Segmentation Using
Watershed Segmentation and Morphological Operation”, International Journal of Research in
Engineering and Technology (IJRET), vol. 03, 2014

[7] Meiyan Huang, Wei Yang, Yao Wu, Jun Jiang, Wufan Chen, “Brain Tumor
Segmentation Based on Local Independent Projection-based Classification”, International
Journal of Computer Science and Communication, vol 61, 2014.

Dept. of ECE AITM, Belagavi Page 44

 Identification of Brain tumor using Image processing technique

[8] Roopali R. Laddha1 and Dr. Siddharth A. Ladhake “Brain Tumor Detection Using
Morphological And Watershed Operators”, International Journal of Application or
Innovation in Engineering & Management (IJAIEM), vol 3, 2014.

Dept. of ECE AITM, Belagavi Page 45