Business card recognition is a difficult problem. Characters in business card are small with diverse font types. In this paper, an approach using 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 bigram table as linguistic information to search 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.
|Number of pages||4|
|State||Published - 2001|
|Event||IEEE International Conference on Image Processing (ICIP) 2001 - Thessaloniki, Greece|
Duration: 7 Oct 2001 → 10 Oct 2001
|Conference||IEEE International Conference on Image Processing (ICIP) 2001|
|Period||7/10/01 → 10/10/01|