Presentation 2002/10/11
Verification of FRCM-based Object Recognition Scheme
Kazuya Asahi, Toshinori Watanabe, Ken Sugawara, Takanori Yokoyama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) As one of a 3D object recognition scheme, we are investigating FRCM that expresses the feature of a to-be-recognized object by a multi-dimensional rectangle and recognizes it by using it's similarities to pre-instructed object's feature rectangles. In this report we propose a new scheme of feature extraction using the local structure extracted by the MST(Minimum Spanning Tree) of the gray-scale image. Through experiments we prove that FRCM can realize, using only a few training data, a robust recognition under changes in object placement and illumination.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Shaded Image / Minimum Spanning Tree / Object Recognition / Correlation
Paper # NC2002-61
Date of Issue

Conference Information
Committee NC
Conference Date 2002/10/11(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Verification of FRCM-based Object Recognition Scheme
Sub Title (in English)
Keyword(1) Shaded Image
Keyword(2) Minimum Spanning Tree
Keyword(3) Object Recognition
Keyword(4) Correlation
1st Author's Name Kazuya Asahi
1st Author's Affiliation School of Information Systems, University of Electro-Communications()
2nd Author's Name Toshinori Watanabe
2nd Author's Affiliation School of Information Systems, University of Electro-Communications
3rd Author's Name Ken Sugawara
3rd Author's Affiliation School of Information Systems, University of Electro-Communications
4th Author's Name Takanori Yokoyama
4th Author's Affiliation School of Information Systems, University of Electro-Communications
Date 2002/10/11
Paper # NC2002-61
Volume (vol) vol.102
Number (no) 382
Page pp.pp.-
#Pages 6
Date of Issue