Presentation 1998/1/23
Research on Extraction Contour from Gray Level Image Using Self Organization Map
Hiroomi Takizawa, Yukio Kaneda, Toshio Ito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) An extraction of contour as recognition of object is important. Perivious methods can not extract both large and small contour simultaneously. To solve this issue, we propose a new method which contains self organization map (SOM), pyramid linking and lineprocess. Firstly, we analyze the property of the whole image using SOM. The input vectoor into SOM is line process suggested by Geman and the map is one dimensional histgram. Secondly, we dvide input image into block images adaptively by use of the map and extract one segment from every block. In this paper, we show these algorithm and some experimetal results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) SOM / Line Process / Hough Transformation / Pyramid Linking / Adaptive Block Division
Paper # PRMU97-210
Date of Issue

Conference Information
Committee PRMU
Conference Date 1998/1/23(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Research on Extraction Contour from Gray Level Image Using Self Organization Map
Sub Title (in English)
Keyword(1) SOM
Keyword(2) Line Process
Keyword(3) Hough Transformation
Keyword(4) Pyramid Linking
Keyword(5) Adaptive Block Division
1st Author's Name Hiroomi Takizawa
1st Author's Affiliation Graduate School of Science and Technology, Kobe University()
2nd Author's Name Yukio Kaneda
2nd Author's Affiliation Graduate School of Science and Technology, Kobe University
3rd Author's Name Toshio Ito
3rd Author's Affiliation Electronics Engineering Div., Daihatsu Motor Co.
Date 1998/1/23
Paper # PRMU97-210
Volume (vol) vol.97
Number (no) 501
Page pp.pp.-
#Pages 8
Date of Issue