Title :
Handwritten numeral recognition with multiple features and multistage classifiers
Author :
Cao, Jun ; Ahmadi, M. ; Shridhar, M.
Author_Institution :
Dept. of Electr. Eng., Windsor Univ., Ont., Canada
fDate :
30 May-2 Jun 1994
Abstract :
Multiple expert system is shown to be a promising strategy for handwritten numeral recognition. This paper presents a multiple expert system using neural networks. In the proposed system, the authors have developed (1) an incremental clustering neural network algorithm with merging and canceling process, (2) a modified directional histogram feature extraction method and (3) a subclass method with learning rejection neuron strategy. Our experimental results on a large set of data show the efficiency and robustness of the proposed system
Keywords :
character recognition; expert systems; feature extraction; learning (artificial intelligence); merging; neural nets; pattern classification; canceling process; feature extraction method; handwritten numeral recognition; incremental clustering neural network algorithm; learning rejection neuron strategy; merging; modified directional histogram; multiple expert system; multiple features; multistage classifiers; robustness; subclass method; Clustering algorithms; Expert systems; Feature extraction; Handwriting recognition; Histograms; Merging; Neural networks; Neurons; Robustness; Smoothing methods;
Conference_Titel :
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location :
London
Print_ISBN :
0-7803-1915-X
DOI :
10.1109/ISCAS.1994.409591
