Presentation 2011-12-16
Example-based Generic Object Detection Using Similar-Image Search
Yuki WATANABE, Hiroto NAGAYOSHI, Atsushi HIROIKE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose an object detection method using similar-image search, which can be applied to various categories of object. For each object candidate, our method find a nearest neighbor example from database, and evaluate it by similarity. To reduce the cost of nearest neighbor search, we use coarse-to-fine approach, and fast vector search method of similar-image search engine. By adding a small set of examples, our method can detect a wide variety of objects in a practical time.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) object detection / nearest neighbor search / similar-image search / local edge-pattern features
Paper # PRMU2011-142
Date of Issue

Conference Information
Committee PRMU
Conference Date 2011/12/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Example-based Generic Object Detection Using Similar-Image Search
Sub Title (in English)
Keyword(1) object detection
Keyword(2) nearest neighbor search
Keyword(3) similar-image search
Keyword(4) local edge-pattern features
1st Author's Name Yuki WATANABE
1st Author's Affiliation The Central Research Laboratory, Hitachi Ltd.()
2nd Author's Name Hiroto NAGAYOSHI
2nd Author's Affiliation The Central Research Laboratory, Hitachi Ltd.
3rd Author's Name Atsushi HIROIKE
3rd Author's Affiliation The Central Research Laboratory, Hitachi Ltd.
Date 2011-12-16
Paper # PRMU2011-142
Volume (vol) vol.111
Number (no) 353
Page pp.pp.-
#Pages 6
Date of Issue