Automatic Cataract Classification on Retinal Image using Support Vector Machine

Abstract

Abstract-Eye is a delicate organ of the body which provides organisms a vision. Eye is made up of sensory component such as lens, pupil, retina etc. One of the diseases which affect the human eye is cataract. Cataract occurs due to clouding of lens in the eye. Cataract is an eye disease which is responsible for vision loss and blindness. But earlier cataract detection system can provide a patient to know their condition timely and they can get the treatment accordingly. Using various image processing and classification technique one can detect and classify images. This paper points out different algorithm for detecting cataract in fundus images. This paper mainly involves mainly three steps specially preprocessing of the image, extraction of feature of preprocessed image and the last one is classification of image. In the very first step, image processing technique is applied for processing the image. We have used brightness preserving dynamic fuzzy histogram equalization method for contrast enhancement of image. In second step various feature of optical eye is extracted and the same feature are then used in classifier. For feature extraction statistical texture features such as mean, variance, energy, entropy and kurtosis of the eye is found. Support Vector Machine (SVM). SVM classification accuracy is 89%.

Enhancing Privacy and Security in Personalized Web Search

“…Kumari et al in [6], discussed Support Vector Machine (SVM), a machine learning method as the classifier for diagnosis of diabetes. It used datasets for diabetes disease from the machine learning laboratory at University of California, Irvine.…”

Decision Support System for Diabetes Mellitus through Machine Learning Techniques

“…The most important AI techniques that have been used by researchers are Artificial Neural Network (ANN), Support Vector Machine, Fuzzy Logic systems, K-mean classifier, and many others [3,[7][8][9][10][11]. ANN is considered to be the most popular one among all.…”

“…Matlab program is used to build the DM treatment based ANN classifier sub model. The network has been trained based on back propagation algorithm, the network receives the 11 features [3,24].…”

“…In this work, the same algorithm is used for training the ANN to forecast the FBS rate for DM patients. The www.ijacsa.thesai.org only thing that changed with the presented ANN is the number of the selected significant features [3], the network receives 10 features.…”

“…Consequently, numerous research works have been conducted to analyze and categorize the DM patient types [3,4]. Most of researchers have depended further on artificial intelligence (AI) and data mining (DM) techniques for constructing their classifier or forecaster models.…”