Abstract | ||
---|---|---|
In this paper, we propose a novel method for fast nearest neighbors retrieval in non-Euclidean and non-metric spaces. We organize the data into a hierarchical fashion that preserves the local similarity structure. A method to find the approximate nearest neighbor of a query is proposed, that drastically reduces the total number of explicit distance measures that need to be computed. The representation overcomes the restrictive assumptions in traditional manifold mappings, while enabling fast nearest neighbor's search. Experimental results on the Unipen and CASIA Iris datasets clearly demonstrates the advantages of the approach and improvements over state of the art algorithms. The algorithm can work in batch mode as well as in sequential mode and is highly scalable. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICAPR.2009.99 | Kolkata |
Keywords | Field | DocType |
casia iris,novel method,nearest neighbors retrieval,sequential mode,robust approximate nearest neighbor,batch mode,hierarchical local maps,art algorithm,nearest neighbor,approximate nearest neighbor,explicit distance measure,artificial neural networks,manifold learning,indexation,manifolds,databases,accuracy,metric space,approximation theory,indexing,iris | k-nearest neighbors algorithm,Fixed-radius near neighbors,Pattern recognition,Computer science,Best bin first,Nearest neighbor graph,Artificial intelligence,Nearest-neighbor chain algorithm,Nonlinear dimensionality reduction,Cover tree,Nearest neighbor search | Conference |
ISBN | Citations | PageRank |
978-1-4244-3335-3 | 0 | 0.34 |
References | Authors | |
6 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pratyush Bhatt | 1 | 0 | 0.34 |
Anoop M. Namboodiri | 2 | 255 | 26.36 |