コンテンツメニュー

Improvements of document understanding system for handwritten address image

大島商船高等専門学校紀要 Volume 38 Page 47-52
published_at 2005-12
OS10038000008.pdf
[fulltext] 4.45 MB
Title
手書き宛名画像を対象とした文書理解システムの改良
Improvements of document understanding system for handwritten address image
Creators Morimoto Hayato
Creators Okamura Kenshiro
Creators Tanaka Yuuki
Creators Suehiro Koujiro
Source Identifiers
Creator Keywords
document understanding system address reading character segmentation
This paper proposes a method of document understanding system for handwritten address image. In a previous work, the performance of rough classification is low, and final outputs are not so accurate. The causes of these problems are low rate of character recognition and fault of knowledge-based processing. To avoid these problems, the proposed method uses multiple candidates for the character recognition and reselects most available one by using address phrases. Furthermore, by changing the priority in rough classification and giving the dynamical threshold in rough classification, the method can overcome the fault of the knowledge-based processing. In experimental results, the effectiveness of our method has been proven.
Languages jpn
Resource Type departmental bulletin paper
Publishers 大島商船高等専門学校
Date Issued 2005-12
File Version Version of Record
Access Rights open access
Relations
[ISSN]0387-9232
[NCID]AN00031668