This project aims to classify different types of fruits using deep learning. The objective is to build a model that can accurately identify the type of fruit based on images.

Built a deep learning model for flower image classification using the pre-trained MobileNetV2. By fine-tuning this lightweight CNN, the system accurately identifies flower species with efficient performance, making it suitable for real-time and resource-constrained environments.

This repository contains the source code and documentation for the Waste Classification project. The project includes a Laravel-based web backend, Python prediction scripts, and a Jupyter notebook with experiments and analysis.

Polyp segmentation on the Kvasir-SEG dataset using deep learning models like UNet, UNet++, PSPNet, and DeepLabV3Plus with ResNet50 and MobileNetV2 encoders.

This repository contains a Python application for emotion recognition using facial expressions. The application utilizes computer vision techniques and deep learning models to analyze facial expressions , aiming to detect and classify emotions based on input images or video streams.

Lightweight rice leaf disease classification using a custom Spatial Attention-augmented MobileNetV2 built from scratch, achieving higher accuracy without increasing parameters or FLOPs.

BreedNet is a deep learning application that identifies cat and dog breeds using MobileNetV2 and transfer learning. Trained on the Oxford IIIT Pet Dataset, it features a Gradio web interface for real-time image uploads and breed predictions with confidence scores.

An end-to-end computer vision project that trains a CNN to classify vegetables and deploys it to Android.

Real-time face mask detection system using MobileNetV2 (CNN) and OpenCV's DNN-based face detector. Applies multiple denoising techniques (Gaussian, Median, Bilateral, FastNlMeans) to improve accuracy. Classifies faces into three categories: Mask, No Mask, and Improper Mask

An AI-powered web application for early detection of skin cancer, burns, and infections using deep learning (MobileNetV2). Trained on diverse medical datasets, the system achieved 90%+ accuracy and provides real-time predictions through a user-friendly interface.

An AI-powered web application that classifies fruits as fresh or rotten using MobileNetV2 transfer learning, TensorFlow, Flask, and computer vision techniques.

This is an official pytorch implementation of WideHRNet: an Efficient Model for Human Pose Estimation Using Wide Channels in Lightweight High-Resolution Network.

🧠 Detect brain tumors from MRI scans using MobileNetV2 deep learning! 86.6% accuracy with transfer learning. Complete EDA, visualization, and production-ready code.