Using hidden Markov model for Chinese business card recognition

Author

Wang, Yuan-Kai ; Fan, Kuo-Chin ; Juang, Y.T. ; Chen, T.H.

Volume

1

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

1106

Abstract

Business card recognition is a difficult problem. Characters in business card are small with diverse font types. An approach using the left-right hidden Markov model is proposed for business card recognition. The hidden Markov model will output a top-10 candidate list as its recognition result. A postprocessing stage is followed to improve the recognition result. The postprocessing stage uses a bigram table as linguistic information to search for the optimized recognition result from the top-10 candidate list. Our experiments are built on the recognition of company item and address item in Chinese business cards. Bigram table and hidden Markov models are trained with a telephony database. 100 address items and 30 company items are used for testing. Experimental results reveal the validity of our proposed method

Keywords

document image processing; feature extraction; hidden Markov models; learning (artificial intelligence); linguistics; optical character recognition; Chinese business card recognition; OCR; address item; bigram table; company item; feature extraction; hidden Markov model; linguistic information; optical character recognition; optimized recognition result; postprocessing stage; telephony database; Character recognition; Companies; Databases; Feature extraction; Hidden Markov models; Natural languages; Optical character recognition software; Speech recognition; Stochastic processes; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2001. Proceedings. 2001 International Conference on

Conference_Location

Thessaloniki

Print_ISBN

0-7803-6725-1

Type

conf

DOI

10.1109/ICIP.2001.959243

Filename

959243