Title :
Image recognition using extended BAM neural networks
Author :
Zhenjiang, Miao ; Baozong, Yuan
Author_Institution :
Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China
fDate :
27 Jun- 2 Jul 1994
Abstract :
In this paper, we present an extended bidirectional associative memory (BAM) neural network approach to image recognition. This approach is characterized by the following important properties due to its associative memory: 1) it has the features of great adaptivity, robustness and fault tolerance to carry out recognition; 2) the recognition system constructed allows for the formation of arbitrary nonlinear decision surfaces; and 3) the recognition system can perform not only the recognition task but also restore the correct information from incomplete even some extent incorrect information at the same time. Experiments are also conducted and the results show that this approach is very efficient and has great application potentials
Keywords :
content-addressable storage; image recognition; image restoration; neural nets; extended bidirectional associative memory neural network; fault tolerance; image recognition; image restoration; nonlinear decision surfaces; Associative memory; Character recognition; Fault tolerant systems; Hopfield neural networks; Image recognition; Image restoration; Magnesium compounds; Neural networks; Robustness; Shape;
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.1994.374876
