A character-based postprocessing system for handwritten Japanese address recognition

Based on a previous work on handwritten Japanese kanji character recognitio n [1], a postprocessing system for handwritten Japanese address recognition is proposed. Basically, the recognition system is composed of CombNET-II, a general-purpose large-scale character recognizer and MMVA, a modified maj ority voting system. Beginning with a set of character candidates, produced by a character recognizer for each character that composes the input word and a lexicon, an interpretation to the input word is generated. MMVA is us ed in the postprocessing stage to select the interpretation that accumulate s the highest score. In the ease of more than one possible interpretation, the Conflict Analyzing System calls the character recognizer again to gener ate scores for each character that composes each interpretation to determin e the final output word. The proposed word recognition system was tested wi th 2 sets of handwritten Japanese city names, and recognition rates higher than 99% were achieved, demonstrating the effectiveness of the method.