Image Recognition and Retrieval Engine
See demo on location:
How it works
ID-Search uses image recognition to index an image collection. It creates a unique fingerprint for each image in the collection and does not use any data associated with the images
to create the image recognition based fingerprint. These unique digital fingerprints describe the patterns found in the pixels of the images. ID-Search is able to identify even partial
matches of these fingerprints.
ID-Search creates an index of all the images’ fingerprints for reference and stores them in an internal database.
API calls are used to add images to the index and to search through existing images.
Image matching is quick, and scales to handle hundreds of millions of images.
Technologies
Frontend: Bootstrap & Angular JS
Backend: Web API 2 & Mongo DB & Unity
Implemented features
Relevance feedback algorithms: Rocchio & Relevance Feature Estimation
Image features: MPEG 7