Title :
An improved classification for cursive script recognition
Author :
Duneau, Laurent ; Dorizzi, Bernadette
Author_Institution :
Inst. Nat. des Telecommun., Evry, France
Abstract :
The authors present a system able to recognize English words dynamically written on a digitizing tablet. It relies on a statistical approach, in which letters are first identified with a certain likelihood. A score is then given to each word in the dictionary for the final recognition. In order to optimize the allograph identification phase, a hierarchical classification algorithm allows one to group the allographs corresponding to a given letter and a given size. Performances on a database of 5000 words and a dictionary of 1000 words are very good and the extension to multi-scriptors is possible thanks to a partial relearning
Keywords :
handwriting recognition; optical character recognition; pattern classification; statistical analysis; word processing; English words; allograph identification phase; cursive script recognition; database; dictionary; digitizing tablet; hierarchical classification algorithm; multi-scriptors; partial relearning; statistical approach; Classification algorithms; Clustering algorithms; Databases; Dictionaries; Feature extraction; Frequency; Microcomputers; Performance evaluation; Prototypes; Supervised learning;
Conference_Titel :
Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on
Conference_Location :
Tsukuba Science City
Print_ISBN :
0-8186-4960-7
DOI :
10.1109/ICDAR.1993.395606
