This is a course project done for E9 246: Advanced Image Processing course. The goal of the project was to develop an android app for real-time object detection using YOLOv5. The app is developed using Pytorch Mobile and Android Studio. YOLOv5 model is trained on PASCAL-VOC dataset and is converted to a mobile-optimized format for PyTorch models to deploy on Android devices. slides
This is a course project done for E0 259: Data Analytics course. The goal of the project was to find out the importance of different regions in fundus images for classifying diabetic retinopathy. The results show that deep learning model performs better when the fundus images are cropped around fovea region followed by optic disc region and middle part of the fundus images. report slides