Professional Documents
Culture Documents
Submitted by
APRIL 2023
NANDHINI SB(950819106047)
ASHA S (950819106007)
SIGNATURE SIGNATURE
CERTIFICATE EVALUATION
I
College Name : Government College of Engineering, Tirunelveli-627 007
2 Mari Ashwini B
(950819106038)
3 Nandhini S B
(950819106047)
4 Asha S
(950819106007)
The report of the project work submitted by the above students in fulfillment for
the award of Bachelor of Engineering in Electronics and Communication
Engineering of Anna University was evaluated and confirmed to be the work
done by the above students and then evaluated. Submitted for the Viva-voce
on____________.
ACKNOWLEDGEMENT
First and foremost, we thank the glorious Almighty of God for blessing us
with all that was required for the completion of our project.
I
We are thankful to Dr.S.Sidharthan M.E.,Ph.D., The Principal, Government
College of Engineering, Tirunelveli for his support towards the student
community and nurturing their caliber.
We sincerely thank all our teaching and non-teaching staff for their help in
the completion of our project.
Finally, we thank our friends and family for their encouragement and help
in the execution of our project work.
ABSTRACT
personnel as well as pregnant women who are pregnant. At a young age the
I
pregnancy is still a great time to do the analysis on the condition of the baby in
the womb. But most of this process can only be done by experts, namely
the ultrasound image processing that aims to help medical personnel, patients
are pregnant women and the general public to determine how the development
of the fetus to grow healthy or whether there is any abnormality. The parameters
which will be used as the basis for determining the level of health of the fetus in
early pregnancy, the length of the fetus (Crown Rump Length) and the
Active Contour Models. This method uses the principle of minimizing the
TABLE OF CONTENTS
I
ABSTRACT
LIST OF TABLES
LIST OF FIGURES
1 INTRODUCTION
1.1 GENERAL
1.2 THE IMAGE PROCESSING
SYSTEM
1.2.1 DIGITIZER
1.2.2 IMAGE PROCESSOR
` 1.2.3 DIGITAL COMPUTER
1.2.4 MASS STORAGE
1.2.5 HARD COPY DEVICE
1.2.6 OPERATOR CONSOLE
1.3 IMAGE PROCESSING FUNDAMENTAL
1.3.1 IMAGE PROCESSING
TECHNIQUES
1.3.2 IMAGE ENHANCEMENT
1.3.3 IMAGE RESTORATION
1.3.4 IMAGE ANALYSIS
1.3.5 IMAGE COMPRESSION
1.3.6 IMAGE SYNTHESIS
1.4 APPLICATIONS OF DIGITAL
IMAGE PROCESSING
1.4.1 MEDICAL APPLICATIONS
1.4.2 SATELLITE IMAGING
1.4.3 COMMUNICATION
1.4.4 RADAR IMAGING SYSTEM
1.4.5 DOCUMENT PROCESSING
1.4.6 DEFENCE/INTELLIGENCE
I
2 LITERATURE SURVEY
4 MODULES
4.1 IMAGE SEGMENTATION
4.2 ACTIVE CONTOUR MODEL
4.3 INTEGRAL PROJECTIONS
4.3.1 MODULE 1
4.3.2 MODULE 2
4.3.3 MODULE 3
4.3.4 MODULE 4
5 SOFTWARE SPECIFICATIONS
5.1 MATLAB
5.2 FEATURES OF MATLAB
5.3 INTERFACING WITH
OTHER LANGUAGES
5.3.1 DEVELOPMENT ENVIRONMENT
5.3.2 DEVELOPMENT ALGORITHM
I
AND APPLICATIONS
5.3.3 THE MATLAB LANGUAGE
5.3.4 MATLAB EDITOR
5.3.5 CODE ANALYZER
5.3.6 MATLAB PROFILER
5.3.7 DIRECTORY REPORTS
5.3.8 DESIGNING GRAPHICAL USER
I INTERFACES
5.4 ANALYZING AND ACCESSING DATA
5.4.1 DATA ANALYSIS
5.4.2 DATA ACCESS
5.4.3 VISUALIZING DATA
5.4.4 2-D PLOTTING
5.4.5 3-D PLOTTING AND VOLUME
V VISUALIZATION
5.5 PERFORMING NUMERIC
COMPUTATIONS
6 RESULT ANALYSIS
7 CONCLUSION
8 APPENDIX
9 REFERENCE
LIST OF FIGURES
I
FIG NO. TITLE PAGE NO
PROCESSING SYSTEM
SEQUENCE INVOLVED IN
MONITORING OF FETAL
ULTRASOUND IMAGE
BACKGROUND CONNECTIVITY.
SEGMENTATION PROCESS
OF WORKING
ITERATION PROCESS
I
6.3 IMAGE SEGMENTATION USING
LIST OF TABLES
I
3.1 COMPARISON TABLE ON HEALTHY FETUS
CHAPTER 1
INTRODUCTION
1.1 GENERAL
I
The term digital image refers to processing of a two dimensional picture by
a digital computer. In a broader context, it implies digital processing of any two
dimensional data. A digital image is an array of real or complex numbers
represented by a finite number of bits. An image given in the form of a
transparency, slide, photograph or an X-ray is first digitized and stored as a
matrix of binary digits in computer memory. This digitized image can then be
processed and/or displayed on a high-resolution television monitor. For display,
the image is stored in a rapid-access buffer memory, which refreshes the
monitor at a rate of 25 frames per second to produce a visually continuous
display.
Hard Copy
Device
Display
I
1.2.1 DIGITIZER:
A digitizer converts an image into a numerical representation suitable for
input into a digital computer. Some common digitizers are
1. Microdensitometer
2. Flying spot scanner
3. Image dissector
4. Videocon camera
5. Photosensitive solid- state arrays.
Knowledge Result
Preprocessing Recognition &
interpretation
Base
As detailed in the diagram, the first step in the process is image acquisition
by an imaging sensor in conjunction with a digitizer to digitize the image. The
13
the next step is the preprocessing step where the image is improved being fed as
an input to the other processes. Preprocessing typically deals with enhancing,
removing noise, isolating regions, etc. Segmentation partitions an image into its
constituent parts or objects. The output of segmentation is usually raw pixel
data, which consists of either the boundary of the region or the pixels in the
region themselves. Representation is the process of transforming the raw pixel
data into a form useful for subsequent processing by the computer. Description
deals with extracting features that are basic in differentiating one class of
objects from another. Recognition assigns a label to an object based on the
information provided by its descriptors. Interpretation involves assigning
meaning to an ensemble of recognized objects. The knowledge about a problem
domain is incorporated into the knowledge base. The knowledge base guides the
operation of each processing module and also controls the interaction between
the modules. Not all modules need to be necessarily present for a specific
function. The composition of the image processing system depends on its
application. The frame rate of the image processor is normally around 25 frames
per second.
The secondary storage devices normally used are floppy disks, CD ROMs
etc.
The hard copy device is used to produce a permanent copy of the image
and for the storage of the software involved.
14
The operator console consists of equipment and arrangements for
verification of intermediate results and for alterations in the software as and
when required. The operator is also capable of checking for any resulting errors
and for the entry of requisite data.
Image Enhancement
Image Restoration
IP Image Analysis
Image Compression
Image Synthesis
15
Image enhancement operations improve the qualities of an image like
improving the image’s contrast and brightness characteristics, reducing its noise
content, or sharpening the details. This just enhances the image and reveals the
same information in a more understandable image. It does not add any
information to it.
16
Image synthesis operations create images from other images or non-
image data. Image synthesis operations generally create images that are either
physically impossible or impractical to acquire.
1.4.3 COMMUNICATION:
17
Radar and sonar images are used for detection and recognition of various
types of targets or in guidance and maneuvering of aircraft or missile systems.
1.4.6 DEFENSE/INTELLIGENCE:
18
Clustering, Active Contour , Edge Detection Algorithms and so on. In this
segmentation research on ultrasound images to determine the health of the fetus
will be performed. Prior to the segmentation process, preprocessing should be
done first to improve the quality of ultrasound image, by increasing contrast and
eliminating noise. The Segmentation method used is Active Contour Models
method. This method performs the process by collecting several points which
are then connected and controlled by a line. The output of the segmentation
process is a fetal ultrasound image where the fetus and gestational sac have
been separated from the background object. Furthermore, long measurements
were taken. With this method is expected to lower the quality of ultrasound
image processing can be improved so as to facilitate the determination of fetal
health.
Standard ultrasound - The test uses sound waves to create 2-D images on a
computer screen.
Doppler ultrasound - This test shows and measures the movement of blood
through the uterus, umbilical cord, in the baby’s heart, or around the baby's
body.
19
Ultrasound uses an electronic wand called a transducer to send and receive
sound waves. No radiation is used during the procedure. The transducer is
moved over the abdomen, and sound waves move through the skin, muscle,
bone, and fluids at different speeds. The sound waves bounce off the baby like
an echo and return to the transducer. The transducer converts the sound waves
into an electronic image on a computer screen.
20
CHAPTER II
LITERATURE SURVEY
21
.
22
ultrasound data are presented and compared to a set of manual segmentations.
Both visual and quantitative comparisons show the satisfactory results obtained
by this method on the tested data.
CHAPTER III
23
OVERVIEW OF THE PROJECT
3.1.1 DRAWBACKS
1)It requires a very large amount of data in order to perform better than other
techniques.
2)It takes more time to train the dataset.
24
further measurements and then be used to support the diagnostic process. Pre-
processing process is often referred to as low-level processing. At that stage, it
is usually necessary to improve the quality of the image, as well as the process
of detecting the sides or lines of boundaries between different objects, such as
between bone and tissue or between healthy tissue and diseased tissue. Image
analysis in the form of detection or identification of objects can be done through
the process of image classification process to several objects and the process of
comparison between the object characteristics observed with knowledge of the
familiar object characteristics. The process of diagnosis based on the results of
this image processing is not enough just to see the difference in the gray level of
the image elements between the sick and healthy parts, but also through the
differentiation of the size of body parts observed with the body parts under
normal circumstances. The measurement of the magnitude of an object in the
image can be done by counting the number of pixels which states the gray level
of the category of the object. This sonography shows the image of the head of a
fetus in the womb. In the case of pregnancy, Ultrasound (USG) is used by a
gynecologist (DSOG) to estimate the gestational age and estimate the day of
delivery.
25
INPUT IMAGE Marks the fetal processing area and gestational sac
Fetal Segmentation -
Segmentation of Pregnancy Pouch Region Filtering
Determine the health of the fetus, whether the fetus Comparison of diameter - Integral
is healthy or not Projection
3.4.1 GRAYSCALE:
In photography and computing, a grayscale or greyscale digital image is
an image in which the value of each pixel is a single sample, that is, it carries
only intensity information. Images of this sort, also known as black-and-white,
are composed exclusively of shades of gray, varying from black at the weakest
intensity to white at the strongest. Grayscale images are distinct from one-bit bi-
tonal black-and-white images, which in the context of computer imaging are
26
images with only the two colors, black, and white (also called bilevel or binary
images). Grayscale images have many shades of gray in between. Grayscale
images are also called monochromatic, denoting the presence of only one
(mono) color (chrome).Grayscale images are often the result of measuring the
intensity of light at each pixel in a single band of the electromagnetic
spectrum (e.g. infrared, visible light,ultraviolet, etc.), and in such cases they are
monochromatic proper when only a given frequency is captured. But also they
can be synthesized from a full color image; see the section about converting to
grayscale.
27
To find the exact features we have to segment the lung region from the
chest CT scan image for easy computation. For segmenting the lung region
from the chest CT scan image morphological operation is carried out.
28
A={α ∨ property ( α )=TRUE }
Ac={α |α ∉ A }
We introduced the concept of neighborhood connectivity. We now observe that
if an object A is defined on the basis of C-connectivity (C=4, 6, or 8) then the
background Ac has a connectivity given by 12 - C. The necessity for this is
illustrated for the Cartesian grid in Figure 36.
FUNDAMENTAL DEFINITIONS
The fundamental operations associated with an object are the standard set
operations union, intersection, and complement { , , c} plus translation:
29
* Translation - Given a vector x and a set A, the translation, A + x, is defined
as:
A+x={α + x ∨ α ∈ A }
Note that, since we are dealing with a digital image composed of pixels at
integer coordinate positions (Z2), this implies restrictions on the allowable
translation vectors x.
Minkowski addition:
A⊕ B=β ∈ B(A+ β
Minkowski subtraction -
A⊖ B=β ∈ B(A+ β
Dilation:
Erosion:
E(A,B)=A⊖ ( − B )= β ∈ B (A- β
30
FIG 3.4: (A) DILATION D(A,B) (B) EROSION E(A,B)
A binary image containing two object sets A and B. The three pixels in B are
"color-coded" as is their effect in the result.
31
FIG 3.5: CARTESIAN GRID (a) N4 (b) N8
Commutative -
Non-Commutative -
E(A,B)≠ E ( B , A )
Associative -
A⊕ ( B⊕ C )=¿⊕ B⊕ C
Translation Invariance -
A⊕ ( B+ x )=( A ⊕ B )+ x
Duality -
Dc(A,B)=E(Ac,-B)
32
Ec(A,B)=D(Ac,-B)
Non-Inverses -
D(E(A,B),B)≠ A ≠ E ( D ( A , B ) , B )
Translation Invariance-
A⊖ ( B+ x )=( A + x ) ⊖ B=( A ⊖ B ) + x A2
Increasing in A:
D(A1,B)⊂ D ( A , B )
E(A1,B)⊂ E ( A , B )
Decreasing in B:
E(A,B1 )⊃ E 2)
Dilation -
33
A⊕ ( B∪C )=( A ⊕ B ) ∪ ( A ⊕ C )=( B ∪C ) ⊕ A
Erosion-
A⊖ ( B∪C )=( A ⊖ B ) ∩ ( A ⊖ C )
Erosion-
(A⊖ B⊖ C= A ⊖ ( B ⊕C )
MultipleDilations-
nB=(B⊕ B⊕ B ⊕ ......⊕ B
CHAPTER IV
MODULES
34
object or between objects with background contained in an image. With the
process of segmentation, each object in the image can be taken individually so it
can be used as input for other processes. Given the importance of the
segmentation process, it takes a segmentation method that can 2017
International Seminar on Application for Technology of Information and
Communication (iSemantic) 193 perform accurate object separation. Inaccuracy
of the segmentation process may lead to subsequent inaccuracies. In this final
project method used for the segmentation process that is Active Contour
Models.
The concept of Active contours models was first introduced in 1987 and later
developed by various researchers. Active contour uses the principle of
minimizing energy that detects certain features in the image, is a flexible curve
(surface) that can adapt dynamically to the desired edge (edge) or object in the
image (can be used for object segmentation automatically). This system consists
of a set of interconnected and controlled points by a straight line, as shown in
Figure 2.3, Active contour is described as a number of consecutive controlled
points with each other. The determination of objects in the image through active
contour is an interactive process. Users should estimate the initial contour, as
shown in Figure 2.3., The specified contour is almost close to the object feature
form. Furthermore, contour will be attracted towards the feature in the image
because of the influence of internal energy that produces the image. The active
contour parameter for a set of controlled coordinate points in contour can be
defined as follows 1) Where x (s) and y (s) are the coordinates x and y on the
contour and s is the normalization index of the control point. The energy
function described in the active contour consists of two components, namely
internal energy and external energy. The internal force creates a compact curve
(elastic force) and the limits turn very sharply (flexural force). External forces
35
tend to make the curve move toward the boundary of the object. The internal
energy as a sum of elastic energy and flexibility energy can be expressed as
follows :
Region Filtering is used to remove contours away from center points and small
contours by estimating the area of each contour. Contours on fetal cavity images
are selected only on the inner contours only. Contours with an area smaller than
the specified limit value are removed (not considered) from the contour. The
value of the boundary of the contour and radius has been determined based on
the radius that has been selected.
36
4.3.1 MODULE 1:
INPUT IMAGE
● Here, we are giving the collected dataset as input from the system.
4.3.2 MODULE 2:
INPUT IMAGE
PREPROCESSING
4.3.3 MODULE 3:
INPUT IMAGE
PREPROCESSING
SEGMENTATION
37
● broken down into various subgroups called Image segments which helps
in reducing the complexity of the image to make further processing or
analysis of the image simpler. Segmentation in easy words is assigning
labels to pixels. All picture elements or pixels belonging to the same
category have a common label assigned to them. For example: Let’s take
a problem where the picture has to be provided as input for object
detection. Rather than processing the whole image, the detector can be
inputted with a region selected by a segmentation algorithm. This will
prevent the detector from processing the whole image thereby reducing
inference time.
4.3.4 MODULE 4:
INPUT IMAGE
PREPROCESSING
SEGMENTATION
CNN
38
CHAPTER 5
SOFTWARE SPECIFICATION
5.1 GENERAL
39
MATLAB (matrix laboratory),a numerical computing environment
and fourth-generation programming language. Developed by Math Works,
MATLAB allows matrix manipulations, plotting of functions and data,
implementation of algorithms, creation of user interfaces, and interfacing with
programs written in other languages, including C, C++, Java, and Fortran.
In 2004, MATLAB had around one million users across industry and
academia. MATLAB users come from various backgrounds
of engineering, science, and economics. MATLAB is widely used in academic
and research institutions as well as industrial enterprises.
40
applications, and distribute your MATLAB algorithms and applications.
41
makes all this possible. Since so many of the procedures required for Macro-
Investment Analysis involve matrices, MATLAB proves to be an extremely
efficient language for both communication and implementation.
42
messages in the MATLAB command window.
⮚ Automatic variable and function renaming in the MATLAB Editor.
The MATLAB language supports the vector and matrix operations that
are fundamental to engineering and scientific problems. It enables fast
development and execution. With the MATLAB language, you can program
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, MATLAB
eliminates the need for ‘for’ loops. As a result, one line of MATLAB code can
often replace several lines of C or C++ code.
43
This technology, which is available on most platforms, provides
execution speeds that rival those of traditional programming languages.
Scan all the files in a directory and report on code efficiency, file
differences, file dependencies, and code coverage
44
functions.
MATLAB supports the entire data analysis process, from acquiring data
from external devices and databases, through preprocessing, visualization, and
numerical analysis, to producing presentation-quality output.
45
All the graphics features that are required to visualize engineering and
scientific data are available in MATLAB. These include 2-D and 3-D plotting
functions, 3-D volume visualization functions, tools for interactively creating
plots, and the ability to export results to all popular graphics formats. You can
customize plots by adding multiple axes; changing line colors and markers;
adding annotation, Latex equations, and legends; and drawing shapes.
46
5.5 PERFORMING NUMERIC COMPUTATION
CHAPTER 6
SCREENSHOT
47
1
48
FIG 6.3: IMAGE SEGMENTATION USING ACTIVE CONTOUR
MODE:
49
FIG 6.4: THE HEALTH STATUS OF FETUS WILL BE SHOWN AS
OUTPUT COMMAND:
CHAPTER 7
CONCLUSION AND FUTURE SCOPE
7.1 CONCLUSION
50
7.2 FUTURE SCOPE
CHAPTER 8
51
APPENDIX
MATLAB CODE:
clear all;
close all;
I=rgb2gray(I);
fontSize = 16;
imshow(I, []);
axis on;
message = sprintf('Left click and hold to begin drawing.\nSimply lift the mouse
button to finish');
uiwait(msgbox(message));
m = hFH.createMask();
subplot(2,2,3); title('Segmentation');
52
seg = region_seg(I, m, 1000); %-- Run segmentation
figure;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Label the binary image and compute the centroid and center of mass.
binaryImage=m
grayImage=I
% [bw,level]=fcm thresh(grayImage,0)
labeledImage = bwlabel(binaryImage);
area = measurements.Area
centroid = measurements.Centroid
centerOfMass = measurements.WeightedCentroid
perimeter = measurements.Perimeter
numberOfPixels1 = sum(binaryImage(:))
numberOfPixels2 = bwarea(binaryImage)
53
% Get coordinates of the boundary of the freehand drawn region.
structBoundaries = bwboundaries(binaryImage);
% Burn line into image by setting it to 255 wherever the mask is true.
burnedImage = grayImage;
burnedImage(binaryImage) = 255;
subplot(2, 3, 3);
imshow(burnedImage);
axis on;
% Will keep only the part of the image that's inside the mask, zero outside the
mask.
blackMaskedImage = grayImage;
54
blackMaskedImage(~binaryImage) = 0;
subplot(2, 3, 4);
imshow(blackMaskedImage);
axis on;
meanGL = mean(blackMaskedImage(binaryImage));
hold on;
insideMasked = grayImage;
insideMasked(binaryImage) = 0;
subplot(2, 3, 5);
imshow(insideMasked);
axis on;
leftColumn = min(x);
rightColumn = max(x);
topLine = min(y);
bottomLine = max(y);
55
width = rightColumn - leftColumn + 1;
subplot(2, 3, 6);
imshow(croppedImage);
axis on;
hold on;
% Report results.
msgbox(message);
56
fetus_reference=[2.03 0 1.73 2.60 3.83 0 0 3.45 0 0 0 0 4.25]
fetal_length=width*0.01*2;
switch(week_no)
case 1
if(fetal_length>fetus_reference(week_no))
else
end
case 2
if(fetal_length>fetus_reference(week_no))
else
end
case 3
if(fetal_length>fetus_reference(week_no))
else
end
57
case 4
if(fetal_length>fetus_reference(week_no))
else
end
case 5
if(fetal_length>fetus_reference(week_no))
else
end
case 6
if(fetal_length>fetus_reference(week_no))
else
end
case 7
if(fetal_length>fetus_reference(week_no))
else
58
end
case 8
if(fetal_length>fetus_reference(week_no))
else
end
case 9
if(fetal_length>fetus_reference(week_no))
else
end
case 10
if(fetal_length>fetus_reference(week_no))
else
end
case 11
if(fetal_length>fetus_reference(week_no))
else
59
msgbox('InHealthy Infant Fetus');
end
case 12
if(fetal_length>fetus_reference(week_no))
else
end
end
CHAPTER 9
60
REFERENCE
REFERENCES
[4] Sonia Dahdouh, Antoine Serrurier, Gilles Grange, Elsa D.A., Isabelle Bloch.
2014. Segmentation of Fetal Envelope from 3D Ultrasound Images based on
Pixel Intensity Statistical Distribution and Shape Priors. Paris, France.
[5] Adhi Pribadi, Johanes C. Mose, Firman F.W. 2011. Ultrasonografi Obstetri
& Ginekologi. Sagung Seto.
[6] A Dwi Puspitasari, Handayani Tjandrasa. 2011. Deteksi Kepala Janin pada
Gambar USG Menggunakan Fuzzy C-Means (FCM) dengan Informasi Spasial
dan Iterative Randomized Hough Transform (IRHT). Surabaya, Indonesia.
61