Suraj Punj Journal For Multidisciplinary Research ISSN NO: 2394-2886

Shape Based Organ Detection Using

Image Processing
1
Md.Abdul Aziz, 2A.Sai Kumar, 2E.Sai Krishna, 2D.Lakshmi Gayatri, 2G.Gopi Chandh
1
AssistantProfessor,2B.TechStudent
Department of Electronics & Communication Engineering,
Ramachandra College of Engineering, Eluru, Andhra Pradesh,India.

ABSTRACT:

Occurance of disease and obtaining a cure with advant of technology is promising these days where as most
tricky part is the identification of that disease with respective organ.In Medical Image processingimages of the
human body are used for diagnostic and treatment purposes and therefore plays an important role in initiatives to
improve public health In this paper, MRI scan images are used for the analysis.After MRI scan,the image is visually
examined for detection and disease diagnosis.Computer aided methods are used for accurately determining the size,
shape and stage of infected body organ. The processed image is noiseless and efficient. Canny edge deduction
method is usedfor deducting the edges of the image. The filter is applied on the image to obtain clear view of the
image, which later on will help in getting clear boundaries of disease infected areas.

Keywords: Canny edge detection, MRI images,segmentation.

I INTRODUCTION efficient. Canny edge deduction method is usedfor

.Imaging innovation in Medical Science deducting the edges of the image. The filter is applied
made the specialists to analyse the inside bits of the on the image to obtain clear view of the image, which
body for simple determination. It likewise pushed later on will help in getting clear boundaries.
specialists to make Nano surgeries for coming to the
inside segments without truly opening excessively of II PROPOSED SYSTEM:
the body parts. Computerized Tomography Scanner,
When the scope of edge detection stands for
Ultrasound and Attractive Resonance Imaging
efficient medical data represtation
assumed control x-beam,MRI imaging are widely
We are providing medical images of no less vital
used by making the specialists to take a gander at the
information from victim to doctors there will increase
body’s tricky area and measuring the risk involved in
in chance of unidentified or lately identified may
it.Various Picture Handling methods are created for
make the situation worse .Preprocessing of image is
breaking down remote detecting information might
needed.
be altered to break down the yields of restorative
It performs filtering of noise and the other
imaging frameworks to get best-preferred standpoint
artifacts in the image and sharpening the edges in the
to investigate side effects of the patients easily
image. RGB to grey conversion and reshaping also
The image retrieval is used which focus in
take place here. It includes median filter for noise
extracting the properties related visualisation of an
removal. The possibilities of arrival of noise in
image than the textual properties.This system
modern MRI scan are very less. It may arrive due to
involves the shape as essential feature for tokenizing
the thermal effect.
the medical images. This research include several
The Canny edge detection algorithm is known to
processing steps, which are taking input as an image,
many as the optimal edge detector. Canny edge
extracting the features of image in the requirement of
detection is a technique to extract useful structural
the system in this case shape is used as the primary
information from different vision objects and
feature, then classifying the images by shape. Image
dramatically reduce the amount of data to be
processing involves several steps to obtain the
processed. It has been widely applied in various
resultant image. The processed image is noiseless and
computer vision systems. Canny has found that the

Volume 9, Issue 3, 2019 Page No: 828

Suraj Punj Journal For Multidisciplinary Research ISSN NO: 2394-2886

requirements for the application of edge detection on 1) Choose some manner in which to initialize the mi
diverse vision systems are relatively similar. Thus, an to be the mean of each group (or cluster), and do it.
edge detection solution to address these requirements 2) For each example in your set, assign it to the
can be implemented in a wide range of situations. closest group (represented by mi).
The general criteria for edge detection include: If the rounded gradient angle is 0° (i.e. the edge is in
• Gaussian Smoothening Filter the north-south direction) the point will be considered
• Gradient estimations to be on the edge if its gradient magnitude is greater
• Non Maximum Suppression than the magnitudes at pixels in the east and west
• Double Thresholding directions
• Edge Tracking • If the rounded gradient angle is 90° (i.e. the edge is
in the east-west direction) the point will be
Gaussian Smoothing filter : considered to be on the edge if its gradient magnitude
Since all edge detection results are easily affected by is greater than the
image noise, it is essential to filter out the noise to • Magnitudes at pixels in the north and south
prevent false detection caused by noise. directions,
• If the rounded gradient angle is 135° (i.e. the edge
is in the northeast-southwest direction) the point will
beconsidered to be on the edge if its gradient
magnitude is greater than the magnitudes at pixels in
the north west and south-east directions,
Intensity Estimation :
An edge in an image may point in a variety of
directions, so the Canny algorithm uses four filters to
detect horizontal, vertical and diagonal edges in the
blurred images which returns a value for the first • If the rounded gradient angle is 45° (i.e. the edge is
derivative in the horizontal direction (Gx) and the in the north west–south east direction) the point will
vertical direction (Gy). be considered to be on the edge if its gradient
magnitude is greater than the magnitudes at pixels in
the north east and south west directions.

Non Maximum Supression :

Non-maximum suppression is applied to find "the
largest" edge.
On Comparing the edge strength of the current pixel
with the positive and negative gradient directions, the
largest compared to the other pixels in the mask with
the same direction will be preserved.
Double Thresholding :
By selecting high and low threshold values, if an
edge pixel’s gradient value is higher than the high
threshold value, it is marked as a strong edge pixel,
otherwise it is treated as a weak edge pixel.
1. Compare the edge strength of the current pixel .
with the edge strength of the pixel in the positive and Fig 1:proposed system block diagram
negative gradient directions.
2. If the edge strength of the current pixel is the III METHODOLOGY :
largest compared to the other pixels in the mask with
the same direction (i.e., the pixel that is pointing in Pre-Processing :
the y-direction, it will be compared to the pixel above MRI images can be affected to
and below it in the vertical axis), the value will be noise, which can be occurred during the transmission
preserved. Otherwise, the value will be suppressed. of images. The noises of the images have been

Volume 9, Issue 3, 2019 Page No: 829

Suraj Punj Journal For Multidisciplinary Research ISSN NO: 2394-2886

reduced and the unwanted data has been cropped is obtained . algorithm. It was tested with providing
manually. Enhancement of data is necessary for the with the test image of various organs.
best possible result, which will help down in IV SIMULATION RESULTS :
narrowing towards our goal.

Feature Extraction :
In image processing all the images are
classified under certain features which are texture,
shape3, colour. Feature extraction is an integral part
of image processing which helps in narrowing down
our dataset to achieve our goal. The identified feature
is taken as the input in the system based on which the
organs will be classified and stored in the database.
In the gray scale images the gray levels helps in
determining the pixel and its relevant position. By
identifying the core pixel plotting the neighbouring
pixels becomes more easier. In this system as shape
is taken as primary feature which is also very
important feature in identification, Canny Edge
Detection4 helps in filtering out the edges of the
medical images. In this system for every input image
the shape has been determined for every organ, there
are multiple images taken into consideration for
identifying the edge of one organ to get good result.

Figure : histogram output

The work involved MRI images which pre-

processed manually and narrowed down in one
format. Various features were analysed while
performing the image processing. Among which we
considered shape as a powerful feature in
identification of the organ. Edge detection and with
the help of filter a proper segmented shape of organ

Volume 9, Issue 3, 2019 Page No: 830

Suraj Punj Journal For Multidisciplinary Research ISSN NO: 2394-2886

Figure : intensity gradient using filter method the noise from the processed
image.
This provides costeffective and timely delivery
of dia
gnosis for both physician and patients. The ability to
detect and mark diseases and to identify stone size
and location based on pixel values provide more
efficient analysis of cases. It has demonstrated
potential usefulness in disease diagnosis and
screening, however, the program is only a tool and
the opinion of a qualified medical professional is
required to validate its output
REFERENCES:

1. Thies C, Guld MO, Fischer B, Lehmann

Figure : non-maximum supression
TM, “Content- based queries on the
CasImage database with in the IRMA
framework”, Lec Notes in Comp Sci;
3491:781-92. 2005.
2. Canny, J., “A computational approach to
edge detection”, IEEE Trans on Pattern
Analysis and Machine Intelligence, 8:679-
698, 1986.
3. CBMIR: Shape-Based Image Retrieval Using
Canny Edge Detection And K-mean Clustering
Algorithm For Medical
Images.B.Ramamurthy1,K.R.Chandran2
4. Diagnose Breast Cancer Through Mammograms,
Using Image Processing Techniques and
Figure : final image of canny edge detection Optimization Techniques. Dr. M. Karnan1, K. Rajiv
Gandhi2.
5. An Efficient k-Means Clustering Algorithm:
Analysis and Implementation. Tapas Kanungo,
Senior Member, IEEE, David M. Mount, Member,
IEEE, Nathan S. Netanyahu, Member, IEEE,
Christine D. Piatko, Ruth Silverman, and Angela Y.
VI. CONCLUSION Wu, Senior Member, IEEE. IEEE Transactions On
Pattern Analysis And Machine Int
Image analysis prototype was developed to elligence, 24(7), JULY 2002.
provide technical support in enhanced disease 6.http://www.ijcaonline.org/icvci/number11/icvci145
detection. Its function to pinpoint the organ area as 8.pdf
region of interest, and diseases as objects of interests 7.A Review of Medical Image Classification
provide focused investigation for medical specialists Techniques. Smitha P. Selection grade lecturer Dept.
using image processing methods. Here the program’s of CSE, CE Karunagapally Shaji L. Lecture in
capacity to organize by sequence multiple slices and comp.Appln Dept.of IT, CE, Karunagapally Dr. Mini
combine these based on discernible images of the M. G. Asst. Prof. & HOD Dept. of ECE, MEC
organ allows the physician to evaluate an aggregate Karunagapally International Conference on VLSI,
image from various images that the MRI machine Communication & Instrumentation (ICVCI) 2011
took for each patient. Proceedings published by International Journal of
In this paper, the medical image retrieval Computer Applications(IJCA)
proposed in this system relies on the fetching of 9. Thoma GR, Long LR, Antani SK, Biomedical
image based on its shape which is identify using Imaging research and development: knowledge from
Canny Edge Detection Algorithm, with the help of images in the medical enterprise. Technical Report
canny edge detection we are able to retrieve the Lister Hill National Ctr for Biomedical
border or the outer line of the scanned image and Communications NIH 2006;LHNCBCTR-2006-002.

Volume 9, Issue 3, 2019 Page No: 831