PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Major Project
Reverse Image Search Engine
Finds visually similar images in a collection from a query photo
2-3 weeks build
Overview
Every image in a collection is embedded with a pretrained ResNet-50, and the vectors are stored in a FAISS index. A query photo is embedded the same way and its nearest neighbours returned in milliseconds. The kit compares exact and approximate index types for speed and recall, and exposes search through a FastAPI backend and React gallery.
What makes it stand up
- 01Deep feature embeddings from a pretrained CNN
- 02Flat, IVF and HNSW FAISS indexes compared
- 03Incremental indexing when new images are added
- 04React gallery with drag-and-drop query upload
- 05Recall@k and query latency measured in the report
Module breakdown
- 01
Embedding service
Batch feature extraction with L2 normalisation.
- 02
Index
FAISS index build, save, load and incremental add.
- 03
Search API
FastAPI endpoint returning ranked matches and scores.
- 04
Frontend
React gallery with upload and result grid.
- 05
Evaluation
Recall@k and latency across index types.
After this, you will be able to
- Explain how approximate nearest-neighbour search trades recall for speed
- Defend the choice of index type with measured results
- Demo searching a collection with a photo taken live
Technology stack
- Python
- PyTorch
- FAISS
- FastAPI
- React
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 2-3 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support