Presentation 2004-12-17
Effects of Image Segmentation for Approximating Object Appearance under Near Lighting
Takahiro OKABE, Yoichi SATO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Shading analysis of an object under near lighting is not an easy task, because the direction and distance of the light source vary over the object surface. However, when observing a small area on the surface, techniques assuming far lighting are applicable, because variations of the direction and distance are small in the area. In this paper, we present three contributions to image segmentation for approximating object appearance under near light sources. First, we experimentally evaluate the accuracy of approximations using rectangular segmentation for images of objects under near light sources, and confirm the effects of image segmentation itself. Second, we propose a new segmentation method for approximating images under near light sources Our proposed method plans appropriate segmentations in terms of approximation, depending on object's properties and probability density functions (PDFs) of illumination Finally, we provide implications for some applications including face recognition and forward rendering.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) near lighting / image segmentation / approximation / clustering / illumination distribution
Paper # PRMU2004-148
Date of Issue

Conference Information
Committee PRMU
Conference Date 2004/12/10(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) Effects of Image Segmentation for Approximating Object Appearance under Near Lighting
Sub Title (in English)
Keyword(1) near lighting
Keyword(2) image segmentation
Keyword(3) approximation
Keyword(4) clustering
Keyword(5) illumination distribution
1st Author's Name Takahiro OKABE
1st Author's Affiliation Institute of Industrial Science, The University of Tokyo()
2nd Author's Name Yoichi SATO
2nd Author's Affiliation Institute of Industrial Science, The University of Tokyo
Date 2004-12-17
Paper # PRMU2004-148
Volume (vol) vol.104
Number (no) 524
Page pp.pp.-
#Pages 6
Date of Issue