基于ICA和BP神经网络相结合的掌纹识别

陈智; 黄琳琳

基于ICA和BP神经网络相结合的掌纹识别

陈智,
黄琳琳

北京航空航天大学自动化科学与电气工程学院, 北京 100083

详细信息

中图分类号: TP 391.4
计量
- 文章访问数: 2832
- HTML全文浏览量: 176
- PDF下载量: 1191
- 被引次数: 0
出版历程
- 收稿日期: 2007-06-29
- 网络出版日期: 2008-03-31

Palmprint recognition based on ICA and BP neural network

School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China

摘要

摘要: 提出了一种基于独立成分分析(ICA,Independent Comment Analysis)和多层前馈(BP,Back Propagation)神经网络相结合的方法对掌纹进行识别.首先采用一种新的方法检测角点,得到掌纹图像的不变特征点,根据这些点校正掌纹方向并得到掌纹的感兴趣区域.对该区域采用定点快速ICA算法(FastICA),得到掌纹特征子空间,然后构建BP神经网络,并采用训练样本得到的掌纹特征进行训练,得到合适的权值.对香港理工大学掌纹数据库进行测试,与主成分分析(PCA,Principal Components Analysis)提取特征的方法进行比较,取得了较高的识别率.
- 独立成分分析 /
- 主成分分析 /
- 多层前馈(BP)神经网络 /
- 感兴趣区域 /
- 掌纹识别
Abstract: A novel method based on independent comment analysis (ICA) and back propagation neural network (BPNN) was proposed to solve palmprint recognition. First, a new method was used to detect corner points as the invariant feature points in palm images. Then the palm images were aligned by the points, and the region of interest (ROI) of the images was gotten. In the next place, palmprint features were extracted from the ROI by a fast fixed-point algorithm for ICA (FastICA). By means of this method, the original palmprint ROI images were transformed into a small set of feature space. Finally, the BPNN was trained by the feature spaces of the samples in the training set to get the appropriate weights. After the training, perform palm classification was applied. The method was tested on the Hong Kong Polytechnic University palmprint database. Experimental results show that method based on ICA achieves higher recognition rate than that based on principal components analysis (PCA).
- independent comment analysis /
- principal components analysis /
- back propagation neural network /
- region of interest /
- palmprint recognition

HTML全文

参考文献(1)

[1] Li Wenxin, Zhang David, Xu Zhuoqun. Palmprint identification by fourier transform [J].International Journal of Pattern Recognition and Artificial Intelligence,2002,16(4):417-432 [2] Han C, Cheng H L, Lin C L. Personal authentication using palm-print features[J].Pattern Recognition,2003,36(2): 371-381 [3] Kumar A, Wong D, Shen H. Personal verification using palm-print and hand geometry biometric[J].Lecture Notes in Computer Science,2003,2688:668-678 [4] 吴介,裘正定. 掌纹识别中的特征提取算法综述[J]. 北京电子科技学院学报,2005,13(2): 86-92 Wu Jie, Qiu Zhengding. Survey of feature extraction algorithms in palmprint recognition[J]. Journal of Beijing Electronic Science and Technology Institute,2005,13(2):86-92(in Chinese) [5] 杨竹青,李勇,胡德文. 独立成分分析方法综述[J]. 自动化学报,2002,28(5): 762-772 Yang Zhuqing, Li Yong, Hu Dewen. Independent component analysis: a survey[J]. Acta Automatica Sinica,2002,28(5):762-772(in Chinese) [6] 王明祥. 独立分量分析方法及在图像处理中的应用研究 . 上海:上海大学通信与信息工程学院,2005 Wang Mingxiang. Study on independent component analysis method and its applications to image processing . Shanghai: School of Communication and Information Engineering,Shanghai University,2005(in Chinese) [7] 韩柯,朱秀昌,王汇源. 基于ICA与BP神经网络相结合的人脸识别研究[J]. 信息技术与信息化,2006,2:50-52 Han Ke, Zhu Xiuchang, Wang Huiyuan. Face recognition based on ICA and BP neural network[J]. Information Technology,2006,2:50-52(in Chinese) [8] 范燕,祁云嵩,宋晓宁. 一种基于独立成分分析和径向基神经网络的人脸识别新方法[J]. 江苏科技大学学报(自然科学版),2006,20(4):46-50 Fan Yan, Qi Yunsong, Song Xiaoning. A new method of face recognition based on independent component analysis and neural network with radial basic function[J]. Journal of Jiangsu University of Science and Technology(Natural Science Edition),2006,20(4):46-50(in Chinese) [9] 接标,吴仕勇,齐怀峰. 基于ICA 的在线掌纹识别[J]. 计算机工程与设计,2006,27(18):3433-3435 Jie Biao, Wu Shiyong,Qi Huaifeng. Online palmprint recognition with ICA[J]. Computer Engineering and Design,2006,27(18):3433-3435(in Chinese) [10] 杨淑莹. 图像模式识别[M].北京:清华大学出版社,2005 Yang Shuying. Image pattern recognition[M].Beijing:Tsinghua University Press,2005(in Chinese) [11] 许媛媛. 基于在线掌纹的身份验证技术 . 济南:山东大学控制科学与工程学院, 2005 Xu Yuanyuan. In online palmprint recognition system .Jinan:School of Control Science and Engineering, Shangdong University, 2005(in Chinese) [12] 陈燕新, 戚飞虎. 一种新的提取轮廓特征点的方法[J]. 红外与毫米波学报,1998,17(3):171-176 Chen Yanxin, Qi Feihu. A new method to extract the feature points[J]. Infrared Millim Wave, 1998,17(3):171-176(in Chinese) [13] 张文景, 许晓鸣. 一种基于曲率提取轮廓特征点的方法[J].上海交通大学学报,1999,33(5):592-595 Zhang Wenjing, Xu Xiaoming. Approach to extract feature points on boundary based on curvatur[J]. Journal of Shanghai Jiaotong University,1999,33(5):592-595(in Chinese) [14] Hyvarinen A. Fast and robust fixed-point algorithms for independent component analysis[J]. IEEE Transactions on Neural Networks,1999,10(3):626-633 [15] Yuen P C, Lai J H. Face representation using independent component analysis[J]. Pattern Recognition,2001,34(3):545-553

施引文献

资源附件(0)

访问统计