Presentation 2005-02-03
Image Segmentation Based on Color Quantization Using Self-Organizing Map
Koji TSURUMA, Junji MAEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents the color quantization based on the clustering using a self-organizing map (SOM) and also presents the image segmentation. We propose the new color quantization method based on the modified version of the hierarchical SOM using the two kinds of distance measures in order to use color information effectively. It is expected to perform rough segmentation of the texture regions and segmentation considering the shade regions. The proposed method achieves the stable quantization results by reducing the unnecessary small regions using the pre-processing including the correction of achromatic regions based on a fractal dimension and the smoothing by an anisotropic diffusion. The experimental results demonstrate the effectiveness of the proposed method in comparison with the conventional methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image Segmentation / Color Quantization / Self-Organizing Map / Clustering / Anisotropic Diffusion / Fractal Dimension
Paper # ITS2004-50,IE2004-184
Date of Issue

Conference Information
Committee ITS
Conference Date 2005/1/27(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 Intelligent Transport Systems Technology (ITS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Segmentation Based on Color Quantization Using Self-Organizing Map
Sub Title (in English)
Keyword(1) Image Segmentation
Keyword(2) Color Quantization
Keyword(3) Self-Organizing Map
Keyword(4) Clustering
Keyword(5) Anisotropic Diffusion
Keyword(6) Fractal Dimension
1st Author's Name Koji TSURUMA
1st Author's Affiliation Division of Computer Science and Systems Engineering, Graduate School of Engineering, Muroran Institute of Technology()
2nd Author's Name Junji MAEDA
2nd Author's Affiliation Division of Computer Science and Systems Engineering, Graduate School of Engineering, Muroran Institute of Technology
Date 2005-02-03
Paper # ITS2004-50,IE2004-184
Volume (vol) vol.104
Number (no) 646
Page pp.pp.-
#Pages 6
Date of Issue