Presentation 2001/3/16
Handwritten Character Segmentation by Pixel-Density Detection Agents
Yasuhisa SACHO, Kenshiro OKAMURA, Yoshihiko HAMAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In handwritten document processing system, if the accuracy of character segmentation using the figure-feature increases, the performance of the whole processing system will improve. Most of the conventional methods use connected components or projection histograms of black pixel. However, the conventional figure-feature can not cope with the flexibility of handwritten characters. In this paper, a handwritten character segmentation technique using the agents that observe pixel-density is proposed. Moreover, experiments for handwritten address image shows this method effective.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) handwritten character segmentation / agent / pixel density
Paper # PRMU2000-222
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/3/16(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) Handwritten Character Segmentation by Pixel-Density Detection Agents
Sub Title (in English)
Keyword(1) handwritten character segmentation
Keyword(2) agent
Keyword(3) pixel density
1st Author's Name Yasuhisa SACHO
1st Author's Affiliation Faculty of Engineering, Yamaguchi University()
2nd Author's Name Kenshiro OKAMURA
2nd Author's Affiliation Oshima National College of Maritime Technology
3rd Author's Name Yoshihiko HAMAMOTO
3rd Author's Affiliation Faculty of Engineering, Yamaguchi University
Date 2001/3/16
Paper # PRMU2000-222
Volume (vol) vol.100
Number (no) 702
Page pp.pp.-
#Pages 8
Date of Issue