Presentation 2011-12-15
Generic Object Recognition by Graph Structural Expression
Takahiro HORI, Tetsuya TAKIGUCHI, Yasuo ARIKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a method for generic object recognition using graph structural expression. In recent years, generic object recognition by a computer is strongly requested in the field like the robot vision and the image retrieval. Conventional methods use bag-of-features (BoF) that express the image as an appearance frequency histogram of visual words by quantizing SIFT (Scale-Invariant Feature Transform) features. However, there is a problem that the location information and the relations between keypoints are lost that are important as structural information. To deal with this problem, in the proposed method, the graph is constructed by connecting SIFT keypoints by the line. As a result, the keypoints have the relation, and then structural representation with location information is achieved. Since the graph representation is not suitable for the statistical work, the graph is embedded into a vector space according to the graph edit distance. As a result of two image datasets, the proposed method has improved the recognition rate compared with conventional methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) generic object recognition / graph / SIFT / graph edit distance / vector-space embedding
Paper # PRMU2011-127
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) Generic Object Recognition by Graph Structural Expression
Sub Title (in English)
Keyword(1) generic object recognition
Keyword(2) graph
Keyword(3) SIFT
Keyword(4) graph edit distance
Keyword(5) vector-space embedding
1st Author's Name Takahiro HORI
1st Author's Affiliation Graduate School of System Informatics, Kobe University()
2nd Author's Name Tetsuya TAKIGUCHI
2nd Author's Affiliation Organization of Advanced Science and Technology, Kobe University
3rd Author's Name Yasuo ARIKI
3rd Author's Affiliation Organization of Advanced Science and Technology, Kobe University
Date 2011-12-15
Paper # PRMU2011-127
Volume (vol) vol.111
Number (no) 353
Page pp.pp.-
#Pages 6
Date of Issue