Centralized Disaster Response and Inventory Management System that leverages AI and Google Cloud Technologies to predict disasters, optimize resource management, and provide real-time coordination.

This project demonstrates deep learning-based segmentation of retinal blood vessels from fundus images using a U-Net architecture with an EfficientNetB4 encoder. The goal is to segment vessel structures, a crucial step in diagnosing conditions like diabetic retinopathy, glaucoma, and hypertension.Model:U-Net with a pretrained EfficientNetB4 encoder

The Pizza Topping Classification project is centered around developing a deep learning model capable of automatically identifying different pizza toppings from images.

A project on building deep learning classifier to classify playing cards

Compare the performance of four deep learning models—CNN, MobileNetV3 Large, VGG16, and EfficientNetB4—for the automated detection and classification of skin lesions

A 5-layer CNN model for facial emotion recognition trained on FER-2013. Achieved 76% validation and 63% test accuracy using data augmentation. Key features include convolutional layers, max pooling, and dropout. Suitable for human-computer interaction applications.

A deep learning project for classifying seven core emotions from facial expressions using transfer learning on RGB images. Focused on model performance, efficiency, and real-world applicability.