Oculi Check is a cutting-edge deep learning model based on the Xception architecture, designed to predict common eye diseases such as glaucoma, diabetic retinopathy, and cataract from retinal images. This project aims to provide a tool for early diagnosis and management of these conditions, helping to prevent vision loss and improve patient outcomes.
Retinal diseases like diabetic retinopathy, glaucoma, and cataracts cause significant vision loss. Current manual diagnostic methods are slow and error-prone, with a shortage of specialists leading to delays. Existing tools lack advanced AI capabilities, resulting in inefficient analysis. Patients face delayed treatment, risking blindness, while ophthalmologists and healthcare systems are overwhelmed, especially in low-resource areas. The ultimate goal is to create a tool for early diagnosis so that early treatment can be provided to patients.
- Introduction
- Features
- Installation
- Usage
- Dataset
- Model Architecture
- Results
- Contributing
- License
- Acknowledgements
Early detection of eye diseases is crucial for effective treatment and management. Oculi Check leverages the power of deep learning to analyze retinal images and provide accurate predictions for glaucoma, diabetic retinopathy, and cataract. Our model is built on the Xception architecture, known for its efficiency and accuracy in image classification tasks.
- High Accuracy: Achieves state-of-the-art performance in detecting glaucoma, diabetic retinopathy, and cataract.
- User-Friendly: Simple and intuitive interface for easy use by healthcare professionals.
- Scalable: Designed to handle large datasets and can be integrated into various healthcare applications.
- Open Source: Freely available for community use and contributions.
- Python 3.8 or higher
- TensorFlow 2.x
- Keras
- NumPy
- OpenCV
- Matplotlib
git clone https://github.com/harshilmalhotra/oculi-check.git
cd oculi-check
python app.py
- Harshil Malhotra
- Nityam Sharma
- Aayushi Raj
Working.mp4
