Presentation 1998/1/23
Object-Region extraction in a image
Toru TAMAKI, Tsuyoshi YAMAMURA, Noboru OHNISHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a method for segmenting a color image into object-regions each of which corresponds to the projected region of an object onto an image plane. In conventional segmentation methods, it is not easy to obtain an object as one region. Our proposed method uses geometric features of a region. At first, the image is segmented into small regions. Next, the geometric features, such as inclusion, area ratio, smoothness, and continuity, are calculated in each region. Then the regions are merged based on the geometric features. This merging enables us to get an object-region even if the surface of the object is textured with a variety of reflectances; this isn't taken into account in conventional segmentation methods. Finally we demonstrate the role of each geometric feature in segmentation and show experimental results demonstrating the effectivity of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image segmentation / geometric feature / split and merge / object extraction / object-region
Paper # PRMU97-216
Date of Issue

Conference Information
Committee PRMU
Conference Date 1998/1/23(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) Object-Region extraction in a image
Sub Title (in English)
Keyword(1) image segmentation
Keyword(2) geometric feature
Keyword(3) split and merge
Keyword(4) object extraction
Keyword(5) object-region
1st Author's Name Toru TAMAKI
1st Author's Affiliation Department of Information Engineering, Graduate School of Engineering, Nagoya University()
2nd Author's Name Tsuyoshi YAMAMURA
2nd Author's Affiliation Department of Information Engineering, Graduate School of Engineering, Nagoya University
3rd Author's Name Noboru OHNISHI
3rd Author's Affiliation Department of Information Engineering, Graduate School of Engineering, Nagoya University:Bio-Mimetic Control Research Center, RIKEN
Date 1998/1/23
Paper # PRMU97-216
Volume (vol) vol.97
Number (no) 501
Page pp.pp.-
#Pages 8
Date of Issue