表12 结果

图6 含噪声的测试图像图7噪声滤除后的测试图像

图8 利用ANN训练后的图像图9 测试图像

图10 含噪声的测试图像图11噪声滤除后的测试图像 第五章总结

已经观察到,如果平均误差小于45%,人工神经网络可以用于训练检测从而进行识别。因此,测试图像和原始图像是可识别和成功匹配的。同时也被察到,如果平均误差大于45%,那么图像被识别为不同的图像。在本文中,插入椒盐噪声主要是因为所有用来识别的图像都可能含有某

种噪声,这就需要去滤除噪声,从而进行正确的识别。本文还观察到,由于用来训练的矩阵行数只有原始图像列数的四分之一,用人工神经网络进行训练和测试需要更少的时间。

参考文献

[1] M. Egmont-Petersena, D. de Ridderb, Handelsc,L.Beaurepaire, K.Chehdi; B.V ozel ―Image processing with neural networks—a review\2002, PP-2280–2288 [2] Berend Jan van der Zwaag , Kees Slump , and Lambert Spaanenburg\143-145

[3] Anil K. Jain, Fellow, IEEE, Robert P.W. Duin, and Jianchang Mao,Senior Member, IEEE ―Statistical Pattern Recognition: A Review‖,IEEE TRANSACTIONS ON PATTERN ANALYSIS ANDMACHINE INTELLIGENCE VOL. 22, NO. 1, JANUARY 2000

[4] Andrzej Dziech, Ali Amuri, ―CONTOUR RECOGNITION USING NEURAL NETWORKAPPLICATION‖, Communications Dept.,AGH Cracow University, Cracow, POLAND, Electronics and Communication Dept., Kielce University of Technology, Kielce,POLAND.

[5] Kenji Suzuki, ―Pixel-Based Artificial Neural Networks in Computer-Aided Diagnosis‖, Department of Radiology, Division of Biological Sciences, the University of Chicago USA

[6] N.R. Pal, S.K. Pal, \Recognition 26 (9 (1993 1277– 1284.

[7] S.K. Pal, A. Ghosh, \recognition\–1193

[8] Mostafa Jabarouti Moghaddam, Hamid Soltanian-Zadeh, ―Medical Image Segmentation Using Artificial Neural Networks ―. [9] Adilson Gonzaga, Armando Marin, Evandro A. Silva, Fabiana

C.Bertoni Kelton A.P. Costa, Luciana A.L. Albuquerque ―Neut ral Facial Image Recognition Using Parallel Hopfield Neural Networks‖,Universidade de S?o Paulo

[10] Y.J. Zhang, \

segmentation\– 1340 [11] Humayun Karim Sulehria, Ye Zhang, ―Hopfield Neural Networks—A Survey‖, Proceedings of the 6th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases, Corfu Island,Greece, February 16-19, 2007.