DocumentCode
1376189
Title
Handprinted character recognition based on spatial topology distance measurement
Author
Liou, Cheng-Yuan ; Yang, Hsin-Chang
Author_Institution
Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Volume
18
Issue
9
fYear
1996
fDate
9/1/1996 12:00:00 AM
Firstpage
941
Lastpage
945
Abstract
In this work we present a self-organization matching approach to accomplish the recognition of handprinted characters drawn with thick strokes. This approach is used to flex the unknown handprinted character toward matching its object characters gradually. The extracted character features used in the self-organization matching are center loci, orientation, and major axes of ellipses which fit the inked area of the patterns. Simulations provide encouraging results using the proposed method
Keywords
optical character recognition; self-organising feature maps; topology; center loci; character features; ellipse major axes; handprinted character recognition; orientation; self-organization matching approach; spatial topology distance measurement; Character recognition; Costs; Distance measurement; Feature extraction; Network topology; Neural networks; Pattern matching; Pattern recognition; Robustness; Skeleton;
fLanguage
English
Journal_Title
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher
ieee
ISSN
0162-8828
Type
jour
DOI
10.1109/34.537349
Filename
537349
Link To Document