looking for a database to store descriptors of image features

asked 2016-02-12 07:57:30 -0500

501 - not implemented gravatar image

updated 2016-02-12 07:59:36 -0500

Hello, I'm looking for a database to store my extracted (surf, sift, orb,...) features.

My idea is to use MongoDB as feature store and add each row of image descriptor as document to MongoDB.

MongoDB also includes knn and radius serch algorithms, but I can't estimate how it performs on image features

(curretly I have descriptors with 61 dimensions and more than 10.000.000 features).

Has someone ideas or experiance with mongodb or another socument store?

thank you and best regards

edit retag flag offensive close merge delete

Comments

1

"MongoDB also includes knn and radius serch algorithms" - just curious, got a reference ?

also , be careful, binary descriptors, like orb will need hamming distance, while float descs. like sift work nicely with euclidean(L2)

berak gravatar imageberak ( 2016-02-12 08:24:16 -0500 )edit

Hi, I thought that I can use geoNearfor radius serch (https://docs.mongodb.org/manual/refer...)

501 - not implemented gravatar image501 - not implemented ( 2016-02-15 01:00:42 -0500 )edit

i don't think, it will work with feature2d data

berak gravatar imageberak ( 2016-02-15 01:04:54 -0500 )edit

okay thank you. Any other ideas or solutions? I also can save my descriptors as a binary string

501 - not implemented gravatar image501 - not implemented ( 2016-02-15 07:47:46 -0500 )edit