E-Commerce Product Recommendation System
Pretrained ResNet50 visual embeddings + k-NN search in a real-time Streamlit web interface.
- Feature Extraction: Encoded product images into dense feature vectors using pretrained ResNet50 backbone with Global Max Pooling.
- Visual Search: Applied L2 normalization and brute-force k-Nearest Neighbors (Euclidean distance) search to rank visually similar catalog items.
- Real-Time Interface: Created a Streamlit interface that uploads customer images, infers embeddings on the fly, and displays top recommendations in real time.