Title :
A relational attribute code representation for printed multi-font Chinese character recognition
Author_Institution :
Nanyang Technol. Univ., Singapore
Abstract :
In this paper, a relational attribute code representation is presented for printed multifont Chinese character recognition. This representation reflects the inherent structural information of Chinese characters, and contains sufficiently redundant information so that it can resist some extent of mutation or distortion caused by image capturing or preprocessing. It is invariant to character size or ratio changes. Most Chinese characters can have unique representation
Keywords :
optical character recognition; redundancy; distortion; image capture; image preprocessing; mutation; printed multifont Chinese character recognition; ratio change invariance; redundant information; relational attribute code representation; size change invariance; Character recognition; Data processing; Dictionaries; Feature extraction; Genetic mutations; Office automation; Optical character recognition software; Optical distortion; Paper technology; Resists;
Conference_Titel :
Systems, Man and Cybernetics, 1995. Intelligent Systems for the 21st Century., IEEE International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-2559-1
DOI :
10.1109/ICSMC.1995.538058
