An Off-Line Cursive Handwritten Word Recognition System and Its Application to Legal Amount Interpretation

摘要: Off-line cursive script recognition has got increasing attention during the last three decades since it is of interest in several areas such as banking and postal service. An off-line handwritten word system described this paper used for legal amount interpretation personal checks. The proposed uses a set geometric topologic features to characterize each word. By considering spatial distribution these image, maps into two strings finite symbols. A local associative indexing scheme then on organize vocabulary. When presented with an unknown word, same retrieve candidate words likely match input verification process carried out find best among set. performance been tested image database from real bankchecks. results obtained indicate that able recognize amounts great accuracy.