Presentation 2013-12-12
GPT Correlation for 2D Projection Transformation Invariant Image Matching
Toru WAKAHARA, Yukihiko YAMASHITA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a new technique of 2D projection transformation invariant image matching, GPT (Global Projection Transformation) correlation, as a natural extension of our earlier work, the affine-invariant GAT correlation method. Based on decomposition of 2D projection transformation into a product of affine transformation (AT) and partial projection transformation (PPT), an efficient computational model of GPT determines optimal AT and PPT components that maximize a normalized cross-correlation value between an AT and PPT superimposed input image and a target image. Experimental results using artificially generated images subject to 2D projection transformation show an excellent matching ability of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image matching / distortion-tolerance / 2D projection transformation / normalized cross-correlation
Paper # PRMU2013-76
Date of Issue

Conference Information
Committee PRMU
Conference Date 2013/12/5(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) GPT Correlation for 2D Projection Transformation Invariant Image Matching
Sub Title (in English)
Keyword(1) Image matching
Keyword(2) distortion-tolerance
Keyword(3) 2D projection transformation
Keyword(4) normalized cross-correlation
1st Author's Name Toru WAKAHARA
1st Author's Affiliation Faculty of Computer and Information Sciences, Hosei University()
2nd Author's Name Yukihiko YAMASHITA
2nd Author's Affiliation Graduate School of Engineering and Science, Tokyo Institute of Technology
Date 2013-12-12
Paper # PRMU2013-76
Volume (vol) vol.113
Number (no) 346
Page pp.pp.-
#Pages 6
Date of Issue