Presentation 2020-03-05
A Proposal of Color Quantization Algorithm Based on Weighted Principle Component Analysis Using Saturation
Seiichi Kojima, Tomoki Kusunoki, Yoshiaki Ueda, Noriaki Suetake, Eiji Uchino,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In a 24 bit full color image, there are about 16 millions possible colors. On the other hand, in a limited color image, the color of each pixel is selected from a color pallet which contains very few colors. The colors in a color pallet are called representative colors. A limited color image has smaller file size than a full color image. In order to generate limited color images with small file size, it is necessary to decrease the number of representative colors. However, colorful colors may disappear by reducing representative colors and the quality of the image may be severely degraded. In this report, we propose a color quantization method based on the wighted principle component analysis using saturation. In the proposed method, colorful colors are selected as representative colors preferentially by using saturation as weights. Through experiments, we verify the effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) limited color image / color quantization / principle component analysis
Paper # SIS2019-40
Date of Issue 2020-02-27 (SIS)

Conference Information
Committee SIS
Conference Date 2020/3/5(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Saitama Hall
Topics (in Japanese) (See Japanese page)
Topics (in English) Soft Computing, etc.
Chair Takayuki Nakachi(NTT)
Vice Chair Noriaki Suetake(Yamaguchi Univ.) / Tomoaki Kimura(Kanagawa Inst. of Tech.)
Secretary Noriaki Suetake(Tokyo Metropolitan Univ.) / Tomoaki Kimura(Kindai Univ.)
Assistant Hideaki Misawa(National Inst. of Tech., Ube College) / Yukihiro Bandoh(NTT)

Paper Information
Registration To Technical Committee on Smart Info-Media Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Proposal of Color Quantization Algorithm Based on Weighted Principle Component Analysis Using Saturation
Sub Title (in English)
Keyword(1) limited color image
Keyword(2) color quantization
Keyword(3) principle component analysis
1st Author's Name Seiichi Kojima
1st Author's Affiliation Yamaguchi University(Yamaguchi Univ.)
2nd Author's Name Tomoki Kusunoki
2nd Author's Affiliation Yamaguchi University(Yamaguchi Univ.)
3rd Author's Name Yoshiaki Ueda
3rd Author's Affiliation Fukuoka University(Fukuoka Univ.)
4th Author's Name Noriaki Suetake
4th Author's Affiliation Yamaguchi University(Yamaguchi Univ.)
5th Author's Name Eiji Uchino
5th Author's Affiliation Yamaguchi University(Yamaguchi Univ.)
Date 2020-03-05
Paper # SIS2019-40
Volume (vol) vol.119
Number (no) SIS-458
Page pp.pp.19-22(SIS),
#Pages 4
Date of Issue 2020-02-27 (SIS)