DocumentCode :
275942
Title :
A fully integrated hand-printed character recognition system using artificial neural networks
Author :
Nellis, J. ; Stonham, T.J.
Author_Institution :
Brunel Univ., Uxbridge, UK
fYear :
1991
fDate :
18-20 Nov 1991
Firstpage :
219
Lastpage :
223
Abstract :
The paper presents an integrated strategy for hand-printed optical character recognition. A novel image processing algorithm is proposed that enhances the low frequency features of the input data. Logical neural networks are employed to classify the data. It is recognised that the classification performance will not be error-free due to ambiguities in the data, which cannot be resolved by human interpretation. A contextual post-processor is therefore employed to provide error-correction on the recognition strings. The contextual processor uses dictionary search techniques supported by Viterbi estimators if the input string is not part of the dictionary. The system therefore is not constrained to limited vocabularies
Keywords :
error correction; optical character recognition; Viterbi estimators; ambiguities; artificial neural networks; classification performance; contextual post-processor; dictionary search techniques; error-correction; hand-printed optical character recognition; human interpretation; image processing algorithm; recognition strings;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Artificial Neural Networks, 1991., Second International Conference on
Conference_Location :
Bournemouth
Print_ISBN :
0-85296-531-1
Type :
conf
Filename :
140319
Link To Document :
بازگشت