cataract-detection

This project aim to a build system which helps in the detection of cataract and it's type with the use of Machine Learning and OpenCv algorithms with the accuracy of 96 percent.

A deep learning model built to detect cataract in human eyes using the VGG-19 pretrained weights

Android app which uses Neural architecture to detect the type and grade of the cataract

Cataract detection model

AI-Powered Eye Disease Detection Web App An intelligent retina image classification system built using deep learning (VGG16), TensorFlow, and Flask. This open-source project helps detect common eye diseases like Cataract, Diabetic Retinopathy, and Glaucoma, and also identifies uncertain cases as Unknown.

Lightweight TinyVGG Inspired CNN 1.35M Parameter with Squeeze-and-Excitation blocks for ocular disease classification

Enhancing cataract detection using a MEDNet-based model. Improved accuracy and speed with latent vectors and sampling techniques. Automated early detection for better patient outcomes and reduced ophthalmologist workload.

Cataract classification

Our system works on the detection of cataracts and type of classification on the basis of severity namely; mild, normal, and severe, in an attempt to reduce errors of manual detection of cataracts in the early ages using Machine Learning and Transfer Learning

Cataract Diagnosis using AI and Neural Network

A quantum-powered web application for detecting cataracts in eye images using a hybrid quantum-classical machine learning model.

Design Project: A wearable device for disease detection, by processing image of the eye (Iridology).For the proof of concept and MVP, the software was able to differentiate between a healthy eye, and an eye with a cataract.

Medical computer vision system for cataract screening using YOLOv8 localization and deep learning classification, with reproducible training pipelines and evaluation metrics.

AI-powered mobile app for early-stage cataract detection. Analyze eye images instantly with on-device processing - works offline, no internet required.

AI-powered Cataract Detection & Severity Classification System using Computer Vision, Machine Learning, Deep Learning (SqueezeNet), Flask and OpenCV.

Cataract detection using 5 transfer learning models(MobileNetV2, Xception, ResNet152V2, InceptionResNet2, DenseNet201) with latency benchmarking on T4 GPU.

Eye cataract detection from photographs: HOG+SVM (89.9% acc, 0.03ms) vs fine-tuned YOLOv5 (mAP@0.5 96.6%) on a Roboflow-curated dataset — Master BIAM mini-project

AI-driven diagnostic tool for Cataract detection using Deep Learning. This project implements Convolutional Neural Networks (CNN) to analyze ocular images, providing automated screening to assist in early-stage diagnosis and medical intervention.

Cataract classification from fundus images using a robust model that combines InceptionV3, VGG19, and InceptionResNetV2 through stacking, achieving an accuracy of 98.31%. This advanced approach ensures high precision and sensitivity, making it highly effective in distinguishing between cataract and normal cases.