A radical-partitioned coded block adaptive neural network structure for large-volume Chinese characters recognition
Resource
Neural Networks, 1992. IJCNN., International Joint Conference on
Journal
International Joint Conference on Neural Networks, 1992 IJCNN
Pages
-
Date Issued
1992-06
Date
1992-06
Author(s)
Kuo, J.B.
Mao, M.W.
DOI
N/A
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.>
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
00227109.pdf
Size
393.01 KB
Format
Adobe PDF
Checksum
(MD5):5ba081992fb4e296e1a853e83ecb4586