Real Time Object Detection With MobileNet and SSD

This deep learning project focuses on building a robust air quality classifier from photos using two different deep learning architectures.

Support both image and video real time face mask detection end-to-end

This is a project for my Machine Learning exam. I decided to try a new architecture that I thought up, the architecture consists of a CNN where in each layer there is a positional router, the convolutional experts inside the layers decide by the position of the patches

This project uses a hybrid model combining MobileNet and LSTM to detect deepfakes, addressing the growing threat of AI-generated manipulated media.

A Browser-Based Image AI Transfer Learning Playground.

AI-Powered Universal Bubble Sheet Grader

Utilize mobilenet_v2 and Finetune it with potato disease image dataset (3 classes). App will allow farmers to snap a picture of a plant and determine whether the plant has a disease or not.

Farmakope Apps Klasifikasi Tanaman Herbal

This is a multiclass image classification problem. There data contains images from 6 categories 'buildings','forest','glacier','mountain','sea','street'. The aim is to develop a machine learning model that correctly classifies an input image into one of the categories

Car detection for ADAS using MobileNet CNN — Seminar Project & Paper

BackEnd Sistem Klasifikasi Tanaman Herbal Berbasis AI

Deep Learning framework for mask detection

End-to-end Human Pose Estimation system for real-time exercise analysis with CNN-based age-gender prediction and Flask API deployment.

Fog-assisted real-time intrusion detection and occupancy monitoring system using ESP32, OpenCV, and MobileNet-SSD… combines sensor data (PIR, LDR) with computer vision through multi-modal fusion to deliver low-latency, reliable alerts and live MQTT-based monitoring.

CNN-based crop disease detector for leaf images across 4 crops and 8 classes (Apple, Corn, Potato, Tomato — healthy vs. specific diseases). MobileNetV2 transfer learning with a from-scratch CNN fallback; ~80% val accuracy on a balanced PlantVillage subset. FastAPI inference API + Next.js frontend with drag-and-drop upload and confidence bars.