Title :
A radical-partitioned coded block adaptive neural network structure for large-volume Chinese characters recognition
Author :
Kuo, J.B. ; Mao, M.W.
Author_Institution :
Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Abstract :
A coded block adaptive neural network system using a radical-partitioned structure for a large-volume Chinese character recognition VLSI is presented. Using this coded block adaptive neural network system, 1000 frequently used Chinese characters have been successfully trained in 139.2 h using a 18-MIPS computer. Based on the simulation results, the coded block system with a radical-partitioned structure provided an acceptable learning time, a good recognition rate, and an excellent expansion capability for large-volume Chinese character recognition using a VLSI
Keywords :
VLSI; character recognition; learning (artificial intelligence); neural nets; VLSI; large-volume Chinese characters recognition; learning time; radical-partitioned coded block adaptive neural network structure; recognition rate; Adaptive arrays; Adaptive systems; Character recognition; Computational modeling; Computer networks; Convergence; Neural networks; Neurons; Pattern recognition; Very large scale integration;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227109
