Final-year project catalog

Find a project you can actually build

Working IoT, AI/ML and embedded builds with abstracts, component lists, documentation, and developer support — ready for your final-year submission.

651 projects live
Reset
FYP-DL-MINI-034 Easy
Deep Learning-Based Vehicle Counting & Classification System

This project develops vehicle counting & classification system using a YOLO-based real-time detector trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MAIN-038 Medium
Deep Learning-Based Cataract Detection from Eye Images

This project develops cataract detection from eye images using a GAN-based generative architecture trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MAIN-031 Medium
Speaker Identification & Verification using Deep Learning

This project develops speaker identification & verification using a CNN-LSTM hybrid architecture trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MINI-047 Easy
Cell Image Classification for Cancer Detection using Deep Learning

This project develops cell image classification for cancer detection using a CNN-LSTM hybrid architecture trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MAIN-041 Medium
Text Emotion Detection using Transformer-Based Models

This project develops text emotion detection using a Convolutional Neural Network (CNN) trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MAIN-046 Medium
Deep Learning-Based Forest Fire Detection from Images

This project develops forest fire detection from images using a GAN-based generative architecture trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MAIN-045 Medium
Lip Reading using Deep Learning (Visual Speech Recognition)

This project develops lip reading using a Transformer-based model (BERT/ViT) trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MAIN-043 Medium
Video Summarization using Deep Learning

This project develops video summarization using a ResNet/EfficientNet backbone trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MAIN-048 Medium
Deep Learning-Based Crowd Anomaly & Violence Detection

This project develops crowd anomaly & violence detection using a 3D-CNN for spatio-temporal data trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MAIN-039 Medium
Real-Time Multi-Face Recognition Attendance System

This project develops real-time multi-face recognition attendance system using a CNN-LSTM hybrid architecture trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MAIN-035 Medium
Question Answering System using BERT

This project develops question answering system using a ResNet/EfficientNet backbone trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.

FYP-DL-MAIN-044 Medium
Deep Learning-Based Parking Slot Occupancy Detector

This project develops parking slot occupancy detector using an LSTM/GRU sequence model trained on an appropriate image/video/audio/text dataset. The trained network is optimized for inference speed and served through a real-time demo application.