You are on page 1of 10

IMPROVED VALIDATION OF GLAUCOMA

FROM FUNDUS IMAGES USING DEEP


LEARNING TECHNIQUES

BATCH MEMBERS GUIDE BY

D.Naveenkumar (810018106056) Dr. A.Adaikalam


S.Nithish(810018106058)
G.Sivaseelan(810018106080)
Abstract
• Glaucoma is a group of related eye disorders that cause damage to the optic nerve
that carries information from the eye to the brain which can get worse over time
and lead to blindness. It is very important that glaucoma is detected as early as
possible for proper treatment.

• Proposed system of our project is Convolutional Neural Network (CNN) system for
early detection of Glaucoma.

• The eye images are then pre- processed to remove noise using Gaussian Blur
technique and make the image suitable for further processing. The system is trained
using the pre-processed images and when new input images are given to the system
it classifies them as normal eye or glaucoma eye based on the features extracted.

• Based on this result to improve accuracy, sensitivity and specificity for the early
detection of glaucoma.
Software required

Operating System : Windows 10


Software : MATLABR2014 A
Three Modules

On First Review On Second Review On Third Review

 Input Image and Pre-  Feature Extraction and  Output Classification


Processing Module Training with CNN Module

 Software Requirements  Develop and test with  Complete the software


confirmation and project codes and simulation and test. Try
Installing software and algorithms with different images
check the codes. and outputs.
 Collect the existing  Preparing the coding  Report and Technical
project information for and documentation Documentation
documentation
First Module
Program
clc;
clear all;
close all;
% Read files form pc.
[FileName,PathName] = uigetfile('./Input Image/*.jpg;*.tif;*.bmp;*.jpeg',...
'Select an Input Image File');
In_Img = imread([PathName,FileName]);
figure; imshow(In_Img); title('Input Image');
Im_Res = imresize(In_Img, [512 512]);
figure; imshow(Im_Res); title('Resized Image');
Gr_Img = rgb2gray(Im_Res);
figure; imshow(Gr_Img); title('Gray Image');
R = Im_Res(:,:,1);
G = Im_Res(:,:,2);
B = Im_Res(:,:,3);
figure;
subplot(1,3,1); imshow(R); title('Red Band');
subplot(1,3,2); imshow(G); title('Green Band');
subplot(1,3,3); imshow(B); title('Blue Band');
Input Image
Output Image
References
1. Ahmad, Hafsah, et al. "Detection of glaucoma using retinal fundus
images." 2014 International conference on robotics and emerging allied
technologies in engineering (iCREATE). IEEE, 2014.
2. Atheesan, S., and S. Yashothara. "Automatic glaucoma detection by using
funduscopic images." 2016 International Conference on Wireless
Communications, Signal Processing and Networking (WiSPNET). IEEE, 2016.
3. Sengar, Namita, et al. "Automated detection of suspected glaucoma in digital
fundus images." 2017 40th International Conference on Telecommunications
and Signal Processing (TSP). IEEE, 2017.
4. Almazroa, Ahmed, et al. "An automatic image processing system for glaucoma
screening." International Journal of Biomedical Imaging 2017 (2017).
5. Zhou, Wei, et al. "Automatic optic disc detection in color retinal images by
local feature spectrum analysis." Computational and mathematical methods
in medicine 2018 (2018).
THANK YOU

You might also like