Presentation 2002/6/21
Cluster analysis of color distribution for shadow removal from a still image
Tomoki TSUGAWA, Masashi BABA, Naoki ASADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Although shadows of objects are important information for 3D reconstruction, sometimes they become obstacles to image composition or image recognition, such as person detection. In this paper, we describe a technique of removing the shadow from a still image. By clustering in color space, an image is segmented into shadow regions and sunshine ones. The shadow removal is performed by correcting color and intensity. In experiments, we evaluate the correction method using real images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) shadow removal / clustering / color correction / intensity correction
Paper # PRMU2002-38
Date of Issue

Conference Information
Committee PRMU
Conference Date 2002/6/21(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) Cluster analysis of color distribution for shadow removal from a still image
Sub Title (in English)
Keyword(1) shadow removal
Keyword(2) clustering
Keyword(3) color correction
Keyword(4) intensity correction
1st Author's Name Tomoki TSUGAWA
1st Author's Affiliation Faculty of Information Sciences, Hiroshima City University()
2nd Author's Name Masashi BABA
2nd Author's Affiliation Faculty of Information Sciences, Hiroshima City University
3rd Author's Name Naoki ASADA
3rd Author's Affiliation Faculty of Information Sciences, Hiroshima City University
Date 2002/6/21
Paper # PRMU2002-38
Volume (vol) vol.102
Number (no) 156
Page pp.pp.-
#Pages 6
Date of Issue