Presentation 2007-02-22
Perceptual Segmentation of Natural Color Images Using Hierarchical Algorithm
Akimitsu KAWANO, Hiroto YOKOGISIZAWA, Junji MAEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The purpose of this paper is perceptual segmentation of natural color images containing man-made objects and natural objects. Perceptual segmentation is defined the type of segmentation in which the region of a tree is regarded as one region in contrast to detailed segmentation that considers a tree as many branch regions and leaf regions. We propose the modified hierarchical segmentation algorithm that integrates the L*a*b* components as color features and the statistical geometrical features as texture features by using fuzzy inference. The proposed method is composed of four stages: simple splitting, local merging, global merging and boundary refinement. The comparative experiments with the existing method are performed to demonstrate the effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hierarchical segmentation algorithm / fuzzy inference / L^*a^*b^* color features / statistical geometrical
Paper # ITS2006-48,IE2006-233
Date of Issue

Conference Information
Committee ITS
Conference Date 2007/2/15(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) Perceptual Segmentation of Natural Color Images Using Hierarchical Algorithm
Sub Title (in English)
Keyword(1) Hierarchical segmentation algorithm
Keyword(2) fuzzy inference
Keyword(3) L^*a^*b^* color features
Keyword(4) statistical geometrical
1st Author's Name Akimitsu KAWANO
1st Author's Affiliation Division of Computer Science and Systems Engineering, Graduate School of Engineering, Muroran Institute of Technology()
2nd Author's Name Hiroto YOKOGISIZAWA
2nd Author's Affiliation Division of Computer Science and Systems Engineering, Graduate School of Engineering, Muroran Institute of Technology
3rd Author's Name Junji MAEDA
3rd Author's Affiliation Division of Computer Science and Systems Engineering, Graduate School of Engineering, Muroran Institute of Technology
Date 2007-02-22
Paper # ITS2006-48,IE2006-233
Volume (vol) vol.106
Number (no) 534
Page pp.pp.-
#Pages 6
Date of Issue