Presentation 1998/11/13
Figure-Ground Segmentation method based on Contrast of Regions
Shoji Tanaka, Yuichi Iwadate, Seiji Inokuchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Detecting interesting regions from images has become important in order to reduce the computational complexity associated with time-consuming processes such as object recognition. In this paper, a method for detecting figure regions from picture is presented. The method detects the figure regions based on the level of contrast between a region and its surroundings. Contrast parameters are defined by the color difference and the texture difference between a region and its surroundings, as well as, the focus of the region. A neural network is employed for learning the figure-ground selectivity the in human visual system. Some results of the proposed menthod are also presented.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Attractive Region / Image Segmentation / Neural Network
Paper # HIP98-34
Date of Issue

Conference Information
Committee HIP
Conference Date 1998/11/13(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Figure-Ground Segmentation method based on Contrast of Regions
Sub Title (in English)
Keyword(1) Attractive Region
Keyword(2) Image Segmentation
Keyword(3) Neural Network
1st Author's Name Shoji Tanaka
1st Author's Affiliation ATR Media Integration & Communications Research Laboratories:Department of Systems and Human Science, Osaka University()
2nd Author's Name Yuichi Iwadate
2nd Author's Affiliation ATR Media Integration & Communications Research Laboratories
3rd Author's Name Seiji Inokuchi
3rd Author's Affiliation Department of Systems and Human Science, Osaka University
Date 1998/11/13
Paper # HIP98-34
Volume (vol) vol.98
Number (no) 397
Page pp.pp.-
#Pages 6
Date of Issue