基于PCA-RBF神经网络的手指静脉识别
A Finger Vein Recognition Method Based on PCA-RBF Neural Network

作者: 余成波 * , 谭 俊 * , 余 磊 * , 何 强 , 李 芮 :重庆理工大学远程测试与控制技术研究所;

关键词: 手指静脉识别主成分分析径向基神经网络降维Principal Component Analysis Radial Basis Function Neural Network Finger Vein Recognition Dimensionality Reduction

摘要:
提出了一种将主成分分析法(PCA)和径向基神经网络(RBF)算法相结合的手指静脉分类算法,即PCA-RBF算法。首先对手指静脉训练样本进行PCA降维,提取图像主要成分,利用RBF神经网络分类识别中的优势,对降维后的静脉图像分类,并采用最短距离法进行识别,通过与BP神经网络识别效果的对比试验结果表明PCA-RBF方法加快了手指静脉识别的训练速度、简化了算法结构、提高了识别率。

Abstract:
This paper proposes a finger vein classification algorithm which combines Principal Component Analysis (PCA) with Radial Basis Function (RBF) neural network algorithm, named the PCA-RBF algorithm. Use the training sample to reduce PCA dimensions, and abstract the main component of the image. Because of the advantages of RBF neural network classifying, put finger vein images into different classes, and then use the shortest distance to recognize. Through the experiment result comparing with Back Propagation (BP) neural network, PCA-RBF neural network is better in finger vein recognition. The result shows that PCA-RBF has faster training speed, simpler algorithm and high- er recognition rate.

文章引用: 余成波 , 谭 俊 , 余 磊 , 何 强 , 李 芮 (2012) 基于PCA-RBF神经网络的手指静脉识别。 生物医学, 2, 23-27. doi: 10.12677/HJBM.2012.24006

参考文献

[1] 余成波, 张进, 张一萌. 基于核Fisher鉴别分析的手指静脉识别[J]. 重庆邮电大学学报, 2012, 1: 90-95.

[2] 朱树先, 张仁杰, 郑刚. 基于RBF神经网络的人脸识别[J]. 光学仪器, 2008, 30(2): 31-33.

[3] 王洪斌, 杨香兰, 王洪瑞. 一种改进的RBF神经网络学习算法[J]. 系统工程与电子技术, 2002, 24(6): 103-105.

[4] S. Seshagir, H. K. Khail. Output feedback control of nonlinear systems using RBF neural networks. IEEE Transactions on Neural Networks, 2000, 11(1): 69-79.

[5] 余华, 杨露菁, 李启元. 基于径向基神经网络的语音识别技术[J]. 控制工程, 2009, 16(S2): 90-93.

[6] 张德丰. MATLAB神经网络应用设计[M]. 北京: 机械工业出版社, 2008.

[7] G. B. Huang, P. Saratchandran. A generalized growing and pruning RBF (GGAP-RBF) neural network for function appro- ximation. IEEE Transactions on Neural Networks, 2000, 11(1): 69-79.

[8] A. D. Niros, G. E.Tsekouras. A fuzzy clustering algorithm to estimate the parameters of radial basis functions neural networks and its application to system modeling. Lecture Notes in Com- puter Science, 2008, 5138: 194-204.

分享
Top