Presentation 2004-11-26
A Specific Color Detection Technique for Road Sign Recognition Using Outline Vectors
Hitoshi YAMAUCHI, Hiromitsu TAKAHASHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) As ITS related researches, techniques for extraction and recognition of road signs are actively researched. We presented a technique for extracting image regions which contain road signs in short time. This technique is constructed by detecting colors used for road signs, called as specific colors, and restricting search regions based on histgrams of the colors. We also presented a road sign type recognition technique by using traced outline vectors in extracted regions. Both techniques are based on specific color detection, so the result accuracy is depend on the detection accuracy. In this report, a new specific color detection technique is proposed. This technique is based on RGB values with small calculation amount. The experimental results show that the detection results are stabler and higher accuracy than former. This result improves recognition accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Color Detection / Road Signs / Image Recognition / ITS
Paper # IE2004-88
Date of Issue

Conference Information
Committee IE
Conference Date 2004/11/19(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 Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Specific Color Detection Technique for Road Sign Recognition Using Outline Vectors
Sub Title (in English)
Keyword(1) Color Detection
Keyword(2) Road Signs
Keyword(3) Image Recognition
Keyword(4) ITS
1st Author's Name Hitoshi YAMAUCHI
1st Author's Affiliation Faculty of Computer Science and System Engineering, Okayama Prefectural University()
2nd Author's Name Hiromitsu TAKAHASHI
2nd Author's Affiliation Faculty of Computer Science and System Engineering, Okayama Prefectural University
Date 2004-11-26
Paper # IE2004-88
Volume (vol) vol.104
Number (no) 465
Page pp.pp.-
#Pages 6
Date of Issue