Presentation 1996/10/17
Comparison of Color Space Models in ISODATA Clustering Method
Keiko Takahashi, Keiichi Abe,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This report describes comparison of the eight color spaces: RGB, and five HSV models and two ULCS models, applied to color image segmentation using ISODATA clustering algorithm. We use Mancel standard color chart, which is designed based on human color perception, so that we compare them from the same criterion. In comparing of color space models, it is important whether they suit for a Particular image segmentation method. In this study we adopted the ISODATA clustering method. First we define the necessary conditions of an appropriate color model for ISODATA clustering method, and decide two indices for those conditions: degree of concentration and the average distance between clusters. Then we compute the indices and compare the eight color models.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) color image segmentation / clustering / ISODATA algorithm / color space models / Mancel color chart
Paper # HIP96-22
Date of Issue

Conference Information
Committee HIP
Conference Date 1996/10/17(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) Comparison of Color Space Models in ISODATA Clustering Method
Sub Title (in English)
Keyword(1) color image segmentation
Keyword(2) clustering
Keyword(3) ISODATA algorithm
Keyword(4) color space models
Keyword(5) Mancel color chart
1st Author's Name Keiko Takahashi
1st Author's Affiliation Seirei Gakuen Junior College of Nursing()
2nd Author's Name Keiichi Abe
2nd Author's Affiliation Department of Computer Science Faculty of Information Shizuoka University
Date 1996/10/17
Paper # HIP96-22
Volume (vol) vol.96
Number (no) 306
Page pp.pp.-
#Pages 6
Date of Issue