Research on Algorithms of Gabor Wavelet Neural Network Based on Parallel Structure
Aiming at image target recognition, a novel algorithm of Gabor wavelet neural network based on parallel structure is proposed in this paper, and the system of neural network for multi-target recognition is designed. Based on the characteristics of multi-CPU parallel structure and the parallel property of neural network, the algorithm of Gabor wavelet neural network is proved theoretically. The relevant algorithm structure is designed; the training and recognizing algorithms for image target recognition are given out. Finally, the simulation experiment for 4 types of plane targets indicated that recognition rate reached 98%+, recognizing time was 40ms.
KeywordsHide Layer Parallel Structure Target Recognition Gabor Wavelet Neural Network Algorithm
Unable to display preview. Download preview PDF.
- 1.Zhang, Q., Benveniste, A.: Wavelet networks. [J] IEEE Trans. on NN 3(11), 889–898 (1992)Google Scholar
- 2.Pati, Y.C., Krishnaprasad, P.S.: Analysis and synthesis of feedforward neural network using discrete affine wavelet. Baskshi [J]. IEEE Trans. On NN 4(1), 73–75 (1993)Google Scholar
- 3.Baskshi, B.R., Stephanopoulous, G.: Wave-net: a multiresolution, hierarchical neural network with localized learning. [J] American Institute Chemical Engineer Journal 39(1), 57–81 (1993)Google Scholar
- 6.Kreinovich, V., Sirisaengtaksin, O., Cabren, S.: Wavelet neural networks are asymptotically optimal approximators for functions of one variable. [C]. In: Proceeding of IEEEICNN 1994, Florida, USA, vol. 1, pp. 299–304 (1994)Google Scholar
- 7.Xu, T., et al.: Multi-target recognition with improved BP algorithm. Optics and precision engineering 10, 513–515 (2003)Google Scholar
- 8.Xu, T., et al.: Robust gray image target recognition base on multi-channel Gabor wavelet filters. Optical technique 2, 201–203 (2004)Google Scholar