Efficient Detection of Eye Diseases Using ML AND DL

EasyChair Preprint 12590

Abstract

Detection of eye diseases such as glaucoma,
cataracts, and diabetic retinopathy at an early stage is
crucial for effective treatment and prevention of vision loss. 
In this project, we propose a machine learning (ML) and
deep learning (DL) based approach for automatic detection 
and classification of various eye diseases using retinal
images.
Our proposed system consists of three stages: pre-
processing, feature extraction, and classification. In the pre-
processing stage, we perform image enhancement and
normalization to improve the quality of the retinal images.
In the feature extraction stage, we use convolutional neural
networks (CNNs) to extract discriminative features from the 
preprocessed images. Finally, in the classification stage, we 
use various ML and DL algorithms such as support vector 
machines (SVM), random forests (RFs), and deep neural 
networks (DNN) to classify the retinal images into different
disease categories.
We evaluated our proposed system on a publicly
available dataset containing retinal images ofpatients with
different eye diseases. Our experimental results show that
our proposed approach achieved high accuracy, sensitivity,
and specificity in detecting various eye diseases,
outperforming the state-of-theart methods. Therefore, our
proposed ML and DL

Keyphrases: Convolution Neural Network, deep learning, machine learning

@booklet{EasyChair:12590,
  author    = {Raghu Nandhan Meegada and Ashwan Lingala and Vivek Mamidi and Sai Abhinav Bharadwaj},
  title     = {Efficient Detection of Eye Diseases Using ML AND DL},
  howpublished = {EasyChair Preprint 12590},
  year      = {EasyChair, 2024}}