Presentation 2005-09-22
A Robust Recognition of Objects under Variable Illumination Conditions using Higher-order Local Auto-Correlation
Takayoshi SHIRAKI, Nobuyuki OTSU,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A change of illumination makes it difficult to recognize objects in the real world. Though many methods have tackled this problem, most of them have a weakness for geometrical transformations. In this paper, we treat the case of translation by using Higher-order Local AutoCorrelation (HLAC) features which is invariant under translation. First, we prove the set of HLAC feature vectors of an object with a lambertian surface forms a 3D manifold and is constrained in a linear subspace. Second, we consider such a property and propose a method which is robust to the change of illumination and position by applying a subspace method to HLAC feature vectors.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) illumination / lambertian / HLAC(Higher-order Local AutoCorrelation) / robust
Paper # NLC2005-46,PRMU2005-73
Date of Issue

Conference Information
Committee PRMU
Conference Date 2005/9/15(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) A Robust Recognition of Objects under Variable Illumination Conditions using Higher-order Local Auto-Correlation
Sub Title (in English)
Keyword(1) illumination
Keyword(2) lambertian
Keyword(3) HLAC(Higher-order Local AutoCorrelation)
Keyword(4) robust
1st Author's Name Takayoshi SHIRAKI
1st Author's Affiliation Graduate School of Information Science and Technology, University of Tokyo()
2nd Author's Name Nobuyuki OTSU
2nd Author's Affiliation National Institute of Advanced Industrial Science and Technology:Graduate School of Information Science and Technology, University of Tokyo
Date 2005-09-22
Paper # NLC2005-46,PRMU2005-73
Volume (vol) vol.105
Number (no) 302
Page pp.pp.-
#Pages 5
Date of Issue