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
Visual Fashion Recommender
Finds visually similar clothing from a photo using ResNet embeddings
3-4 weeks build
Overview
Upload a photo of a garment and get visually similar products back. Images from the public Kaggle Fashion Product Images dataset are embedded with a pretrained ResNet-50, indexed with FAISS for fast nearest-neighbour search, and optionally filtered by category and colour. The report compares raw ImageNet features with a model fine-tuned on fashion categories.
What makes it stand up
- 01ResNet-50 embeddings extracted for the whole catalogue
- 02FAISS index for millisecond similarity search
- 03Pretrained versus fine-tuned embeddings compared on retrieval quality
- 04Category and colour filters layered on visual similarity
- 05Upload-a-photo storefront with a similar-items grid
Module breakdown
- 01
Catalogue prep
Cleans images and product metadata.
- 02
Embedding
Batch feature extraction with PyTorch.
- 03
Indexing
FAISS index build, save and query.
- 04
Search API
FastAPI endpoint accepting an image upload.
- 05
Storefront
React grid of matches with filters.
After this, you will be able to
- Explain transfer learning and why embeddings capture style
- Defend approximate nearest-neighbour search at catalogue scale
- Demo similar items for a photo the examiner uploads
Technology stack
- Python
- PyTorch
- FAISS
- FastAPI
- React
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 3-4 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