Title :
Fuzzy feature extraction using a class of neural network
Author :
Wong, Francis ; Wang, P.Z.
Author_Institution :
Inst. of Syst. Sci., Nat. Univ. of Singapore, Singapore
Abstract :
The authors present a novel approach to feature extraction using a class of neural networks for the purpose of authorship recognition. The framework of the research is based on the factor space theory proposed by P.Z. Wang (1990). The main advantage of this approach compared to others is that the dimension of the state space required to distinguish the output patterns for a particular recognition problem can be reduced to the minimum; as a result, both the computation time and the memory storage can be reduced substantially
Keywords :
computerised pattern recognition; fuzzy set theory; learning systems; neural nets; state-space methods; authorship recognition; character recognition; computation time; factor space theory; fuzzy feature extraction; fuzzy set theory; learning systems; memory storage; neural network; pattern recognition; state space; Associative memory; Decision making; Expert systems; Feature extraction; Fuzzy neural networks; Instruments; Knowledge based systems; Neural networks; Pattern recognition; State-space methods;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170360
