UM
A reliability design methodology for Chinese character recognition
Huang Y.S.1; Liu K.3; Suen C.Y.3; Tang Y.Y.2
1998-03-01
Source PublicationInternational Journal of Pattern Recognition and Artificial Intelligence
ISSN02180014
Volume12Issue:2Pages:159-170
AbstractThis paper proposes a novel method which enables a Chinese character recognition system to obtain reliable recognition. In this method, two thresholds, i.e. class region threshold R and disambiguity threshold A, are used by each Chinese character k when the classifier is designed based on the nearest neighbor rule, where R defines the pattern distribution region of character k, and A prevents the samples not belonging to character k from being ambiguously recognized as character k. A novel algorithm to derive the appropriate thresholds A and R is developed so that a better recognition reliability can be obtained through iterative learning. Experiments performed on the ITRI printed Chinese character database have achieved highly reliable recognition performance (such as 0.999 reliability with a 95.14% recognition rate), which shows the feasibility and effectiveness of the proposed method.
KeywordCompetitive learning OCR Rejection Reliable recognition
URLView the original
Language英語
Fulltext Access
Document TypeJournal article
CollectionUniversity of Macau
Affiliation1.Industrial Technology Research Institute of Taiwan
2.Hong Kong Baptist University
3.Universite Concordia
Recommended Citation
GB/T 7714
Huang Y.S.,Liu K.,Suen C.Y.,et al. A reliability design methodology for Chinese character recognition[J]. International Journal of Pattern Recognition and Artificial Intelligence,1998,12(2):159-170.
APA Huang Y.S.,Liu K.,Suen C.Y.,&Tang Y.Y..(1998).A reliability design methodology for Chinese character recognition.International Journal of Pattern Recognition and Artificial Intelligence,12(2),159-170.
MLA Huang Y.S.,et al."A reliability design methodology for Chinese character recognition".International Journal of Pattern Recognition and Artificial Intelligence 12.2(1998):159-170.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Huang Y.S.]'s Articles
[Liu K.]'s Articles
[Suen C.Y.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Huang Y.S.]'s Articles
[Liu K.]'s Articles
[Suen C.Y.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huang Y.S.]'s Articles
[Liu K.]'s Articles
[Suen C.Y.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.