Title :
Neural network designed volume holographic wavelet correlator for pattern recognition
Author :
Feng, Wenyi ; Yan, Yingbai ; Jin, Guofan ; Wu, Minxian ; He, Qingsheng
Author_Institution :
State Key Lab. of Precision Meas. Technol. & Instrum., Tsinghua Univ., Beijing, China
Abstract :
Neural network (NN) techniques have been introduced to design wavelet filters and wavelet transform systems for pattern recognition. Based on the theory of wavelet matched filtering and the associative characteristic of volume holographic storage in a photo refractive crystal, a novel volume holographic wavelet correlator is constructed. A neural network is proposed to optimize parameters of the wavelet filters to improve recognition performance of the system. Simulation and experimental results are given to testify the effect of optimization. Its application in human face recognition is studied. Use of the neural network to refine parameters of filters is attractive
Keywords :
face recognition; filtering theory; holography; neural nets; optical correlation; optimisation; wavelet transforms; human face recognition; neural network; optimization; pattern recognition; volume holographic storage; volume holographic wavelet correlator; wavelet filters; Correlators; Face recognition; Filtering theory; Holography; Humans; Matched filters; Neural networks; Pattern recognition; Testing; Wavelet transforms;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.836177
