Multi-criteria Search Algorithm: An Efficient Approximate K-NN Algorithm for Image Retrieval

Mehdi Badr (1) , Dan Vodislav (1) , David Picard (1) , Philippe-Henri Gosselin (1, 2) , Shaoyi Yin (3)

1 MIDI - Multimedia Indexation and Data Integration
2 TEXMEX - Multimedia content-based indexing
3 IRIT-PYRAMIDE - Optimisation Dynamique de Requêtes Réparties à grande échelle

We propose a new method for approximate k-NN search in large scale image databases, based on top-k multi-criteria search techniques. The method defines a simple index structure based on sorted lists, which provides a good compromise between fast retrieval, storage requirements and update cost. The search algorithm delivers approximate results with guarantees about false negatives, with fast emergence of good approximations, monotonically improved and leading if necessary to an exact result. Experiments with the on-disk implementation show that our method produces very good approximate results several times faster than the Baseline method.

Keywords: top-k algorithms; image databases; CBIR; k-NN search; multi-criteria search

Domains: Computer Vision and Pattern Recognition [cs.CV]; Databases [cs.DB]

Mehdi Badr, Dan Vodislav, David Picard, Philippe-Henri Gosselin, Shaoyi Yin. Multi-criteria Search Algorithm: An Efficient Approximate K-NN Algorithm for Image Retrieval. 2013 IEEE International Conference on Image Processing (ICIP 2013), Sep 2013, Melbourne, Australia. pp.2901-2905, ⟨10.1109/ICIP.2013.6738597⟩. ⟨hal-00832196v2⟩