Integrated object detection, recognition and tracking system using Intel RealSense Depth Cameras

Multi Class Dog Breed Classification

object detection using mobilenetV2 SSDlite model

Using Transfer Learning and TensorFlow to Classify Different Dog Breeds (Machine Learning and Data Science course)

🤖️ Optimized CUDA Kernels for Fast MobileNetV2 Inference

Enhanced MRI Brain Tumor Detection using a Hybrid Deep Learning + Machine Learning model. Combines MobileNetV2 & SVM to classify tumors (Glioma, Meningioma, Pituitary, No Tumor) from contrast MRI. Achieves ~93% accuracy via transfer learning & augmentation.

Face Mask Detector - Open CV & DNN

AI-powered livestock disease diagnostics using MobileNetV2 and Flask. Featuring a high-contrast Modern Brutalist UI for rapid, on-site skin condition analysis.

Implementation of Mobilenet V2 for binary image classification of dogs and cats using Keras and TensorFlow. 📚 Trained on a dataset of dogs and cats images, with customizable scripts for training, testing, and prediction on new data. 📊🛠️

🎯 Identify plant diseases with high accuracy! 🌾💡 | 🌍 Supports multiple plant types 🍎🥔🍓 | 🤖 CNN-based TFLite model for fast predictions 🚀 | 🖥️ Web Interface ready | 🛠️ Python 🐍, TensorFlow Lite 🟠, Flask 🧪

This is a Conv2D model based on MobileNetV2 to first create a facial attribute clasificator which then was used as a pretrained model for a face recognition code. It has an accuracy of ~85% (using my own face to be recognized).

A binary classifier to test whether an image belongs to the "hot dog" class or the "not hot dog" class, as seen on HBO's Silicon Valley.

Detect Malaria from an input Image,Implemented Using Fast.AI

Computer Vision and its application in Autonomous Vehicles

Project Developed for my Bachelor Thesis

A multi task neural network implemented from scratch, performing object detection with SSD and semantic segmentation with DeeplabV3+ simultaneosly!

A robust, real-time Face Mask Detection system built with Python, OpenCV, and TensorFlow. Features automated environment setup, FPS monitoring, and fail-safe execution.

Ano-Unet can visualize abnormal parts.

This is an open source project on the deployment of deep learning to embedded microprocessors. The project establishes a data set for obstacle recognition of blind travel environment, and trains a simplified MoblieNet model in TensorFlow. Finally, the binary file of the model is deployed on the UNCLEO-STM32H7A3ZIT-Q development board to realize …

Developed lightweight MobileNetV2 face mask detection model for identifying a person wearing a mask or not .