Off-line Character Recognition using On-line Character Writing Information

Recognition of variously deformed character patterns is a salient subject for off-line hand-printed character recognition. Sufficient recognition performance for practical use has not been achieved despite reports of many recognition techniques. Our research examines effective recognition techniques for deformed characters, extending conventional recognition techniques using an on-line character writing information containing writing pressure data. This study extends conventional recognition techniques using on-line character writing information containing writing pressure information. A recognition system using simple pattern matching and HMM was made for evaluation experiments using Common Handprinted English character patterns from the ETL6 database to determine effectiveness of the proposed extending recognition method. Character recognition performance is increased in both expansion recognition methods using on-line writing information.

• Type: Conference
• Year: 2003
• Where: ICDAR
• Authors: Hiromitsu Nishimura, Takehiko Timikawa
• Keywords: Character Recognition, Conventional Recognition Techniques, Document Analysis, ICDAR 2003, Recognition Techniques