DocumentCode :
285253
Title :
Two-dimensional neural networks for handwritten Chinese character recognition
Author :
Liao, Hong-Yuan ; Huang, Jun-Shon ; Huang, Shih-Ta
Author_Institution :
Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan
Volume :
3
fYear :
1992
fDate :
7-11 Jun 1992
Firstpage :
579
Abstract :
A two-dimensional Hopfield network approach is proposed to solve the handwritten Chinese character matching problem. The Hopfield net can solve the problem even if the number of strokes in the unknown character and the model character are different. In the recognition stage, the matching rates between the input character and each model character in the database are computed and used to indicate which one is the best match. The proposed technique provides a more general formulation such that some difficult issues in Chinese character recognition like rotational and translation invariance problems are solved. Theory shows that the proposed scheme requires fewer heuristics than other methods. Experimental results are reported using both synthetic and real handwritten Chinese characters to corroborate the theory
Keywords :
Hopfield neural nets; character recognition; database; handwritten Chinese character recognition; neural networks; rotational invariance problems; translation invariance problems; two-dimensional Hopfield network approach; Art; Character recognition; Computer networks; Feature extraction; Handwriting recognition; Hopfield neural networks; Information science; Neural networks; Skeleton; Writing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.227112
Filename :
227112
Link To Document :
بازگشت