Title :
A hybrid method for recognizing handwritten numbers
Author :
Meng, Ye ; Junbo, Fan ; Fan, Jin
Author_Institution :
Inst. of Neural Networks & Inf. Tech., Southwest Jiaotong Univ., Sichuan, China
fDate :
27 Jun-2 Jul 1994
Abstract :
A hybrid method for recognizing handwritten numbers is proposed. This method exploits the power of neural networks, tree classifiers, fuzzy feature extraction and topologic feature extraction. Simulation results demonstrate that this method is efficient
Keywords :
character recognition; feature extraction; fuzzy set theory; image classification; neural nets; topology; trees (mathematics); fuzzy feature extraction; handwritten number recognition; neural networks,; topologic feature extraction; tree classifiers; Classification tree analysis; Education; Feature extraction; Fuzzy neural networks; Handwriting recognition; Multi-layer neural network; Neural networks; Pattern recognition; Shape; Technology planning;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374952
