Hacker News Reader

This is all good, but how does one store, index and efficiently search for near matches? I have a side project with terabytes of photo URLs, and hashing&indexing them has been an itch I could not scratch.

View on HN

Have you looked at https://github.com/dermotte/lire? This plugin for ElasticSearch uses it: https://github.com/kzwang/elasticsearch-image

Looks like it does all kinds of tricks at once -- histograms, SIFT/SURF features and edge patterns. I was looking for a simpler solution, like an effective MVP-tree implementation for perceptual hashes. Wouldn't that be faster and overall better?

Check out metric trees such as the BK-Tree, VP-Tree or GNATs. They allow for fast nearest neighbor searches, for example querying all items in your database with Hamming Distance h < 2.

I stumbled upon metric trees for nearest neighbor queries in metric spaces some months ago and wrote down notes here:

http://daniel-j-h.github.io/post/nearest-neighbors-in-metric...

Hope that helps.

Reply on news.ycombinator.com