基于区域特征映射的模糊掌纹识别方法

魏伟波; 洪丹枫; 潘振宽; 吴鑫

doi:10.16383/j.aas.2015.c131189

基于区域特征映射的模糊掌纹识别方法

doi: 10.16383/j.aas.2015.c131189

1.
青岛大学信息工程学院青岛 266071

基金项目:

国家自然科学基金(61170106),山东省高等学校科技计划(J14LN39)资助

详细信息

作者简介:
洪丹枫青岛大学信息工程学院硕士研究生. 主要研究方向为图像处理, 生物特征识别, 计算机视觉.E-mail: hongdanfeng1989@gmail.com

通讯作者:
魏伟波青岛大学信息工程学院副教授.2006 年获得南京理工大学工学博士学位. 主要研究方向为生物特征识别, 数字图像处理, 目标自动识别与跟踪. 本文通信作者. E-mail: njustwwb@163.com

计量
- 文章访问数: 1943
- HTML全文浏览量: 107
- PDF下载量: 1028
- 被引次数: 0
出版历程
- 收稿日期: 2013-12-30
- 修回日期: 2014-09-01
- 刊出日期: 2015-02-20

Blurred Palmprint Recognition Algorithm Based on Region Feature Map

1.
College of Information Engineering, Qingdao University, Qingdao 266071

Funds:

Supported by National Natural Science Foundation of China (61170106), and Shandong Province Higher Educational Science and Technology Program (J14LN39)

摘要

摘要: 针对掌纹在非接触采集时易出现模糊现象从而导致系统识别性能降低的问题,建立了区域到点的特征映射模型,提出了一种基于区域特征映射(Region feature map, RFM)的模糊掌纹识别方法.首先根据图像的模糊原理,建立等价的模糊模型,获取模糊掌纹; 然后使用RFM对模糊掌纹进行操作,将高维的区域特征映射到低维的点特征; 最后,采用归一化相关性分类器对掌纹所属类别进行判定识别.使用模糊模型对PolyU掌纹库进行处理得到PolyU模糊掌纹库,并分别在PolyU掌纹库和PolyU模糊掌纹库上进行测试,识别结果较为稳定. 在模糊掌纹库上,本文算法的等错误率(Equal error rate, EER)最小可达0.9069%,优于传统算法,且进行一次识别的时间为33.95ms,得到的特征数据维数较小,降低了算法复杂度,表明了本文算法的有效性和实时性.
- 模糊掌纹识别 /
- 模糊模型 /
- 区域特征映射 /
- 归一化相关分类器
Abstract: Capuring palmprints with non-contact devices may lead to the blur phenomenon and degrade the performance of recognition system. In order to address this issue, a mapping model from regions to points is established and a novel recognition approach based on region feature map (RFM) is proposed in this paper. According to the theory of blurred image, an equivalence model is firstly established to obtain blurred palmprint image. Then, high-dimensional regional feature is mapped to low-dimsional point feature by using RFM. Finally, normalized correlation classifier is used for determing palmprint category. Furthermore, the blurred PolyU palmprint database is obtained using blur model, and experiment results are stable in the PolyU and blurred PolyU palmprint database using RFM algorithm. The equal error rate (EER) of the proposed method is 0.9069% in the blurred PolyU palmprint database, which is superior to traditional algorithms. Complexity of the algorithm, and recognition time is only 33.95ms. The effectiveness and real-time performance of our proposed method is verified.
- Blurred palmprint recognition /
- blurred model /
- region feature map (RFM) /
- normalized correlation classifier

HTML全文

参考文献(25)

[1]	Yue Feng, Zuo Wang-Meng, Zhang Da-Peng. Survey of palmprint recognition algorithms. Acta Automatica Sinica, 2010, 36(3): 353-365(岳峰, 左旺孟, 张大鹏. 掌纹识别算法综述. 自动化学报, 2010, 36(3): 353-365)
[2]	Lin Sen, Yuan Wei-Qi, Wu Wei, Fang Ting. Blurred palmprint recognition based on DCT and block energy of principal line. Journal of OptoelectronicsLaser, 2012, 23(11): 2200-2206(林森, 苑玮琦, 吴微, 方婷. 基于离散余弦变换和主线分块能量的模糊掌纹识别光. 电子激光, 2012, 33(11): 2200-2206)
[3]	[3] Wu X Q, Zhang D, Wang K Q, Huang B. Palmprint classification using principal lines. Pattern Recognition, 2004, 37(10): 1987-1998
[4]	Lin Sen, Yuan Wei-Qi. Blurred palmprint recognition under defocus status. Optics and Precision Engineering, 2013, 21(3): 734-741(林森, 苑玮琦. 离焦状态下的模糊掌纹识别. 光学精密工程, 2013, 21(3): 734-741)
[5]	[5] Zuo W M, Zhang D, Wang K Q. Bidirectional PCA with assembled matrix distance metric for image recognition. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2006, 36(4): 863-872
[6]	[6] Shu W Z, Xu X G. Palmprint recognition based on the representation in the feature space. Optik-International Journal for Light and Electron Optics, 2013, 124(22): 5434-5439
[7]	[7] Zhang D, Kong W K, You J, Wong M. Online palmprint identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(9): 1041-1050
[8]	[8] Hong D F, Pan Z K, Wu X. Improved differential box counting with multi-scale and multi-direction: a new palmprint recognition method. Optik-International Journal of Light Electron Optics, 2014, 125(15): 4154-4160
[9]	[9] Hong D F, Wei W B, Wu X, Pan Z K, Li Z H. A novel palmprint recognition algorithm based on region texture description. In: Proceedings of the 2013 International Symposium on Signal Processing, Biomedical Engineering, and Informatics. Hangzhou, China, 2013. 636-645
[10]	Hong D F, Su J, Hong Q G, Pan Z K, Wang G D. Blurred palmprint recognition based on stable-feature extraction using a Vese-Osher decomposition model. PLoS ONE, 2014, 9(7): e101866
[11]	Kong W K, Zhang D, Kamel M. Palmprint identification using feature-level fusion. Pattern Recognition, 2006, 39(3): 478-487
[12]	Yue F, Zuo W M, Zhang D, Wang K Q. Orientation selection using modified FCM for competitive coding-based palmprint recognition. Pattern Recognition, 2009, 42(11): 2841-2849
[13]	Kanhangad V, Kumar A, Zhang D. A unified framework for contactless hand verification. IEEE Transactions on Information Forensics and Security, 2011, 6(3): 1014-1027
[14]	Yuan Wei-Qi, Feng Su-Yue. Simulation system of improved non-contact on-line palmprint recognition. Acta Optica Sinica, 2011, 31(7): 114-119(苑玮琦, 冯素月. 改进的非接触式在线掌纹识别模拟系统. 光学学报, 2011, 31(7): 114-119)
[15]	Kang B J, Park K R. Real-time image restoration for iris recognition systems. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2007, 37(6): 1555-1566
[16]	Fan X, Zhang Q, Liang D Q, Zhao L. Face image restoration based on statistical prior and image blur measure. In: Proceedings of the 2003 IEEE International Conference on Multimedia and Expo. Piscataway, NJ, USA: IEEE, 2003. 297-300
[17]	Wang Guo-Dong, Xu Jie, Pan Zhen-Kuan, Liu Cun-Liang, Yang Jin-Bao. Blind image restoration based on normalized hyper Laplacian prior term. Optics and Precision Engineering, 2013, 21(5): 1341-1347(王国栋, 徐杰, 潘振宽, 刘存良, 杨金宝. 基于归一化超拉普拉斯先验项的运动模糊图像盲复原. 光学精密工程, 2013, 21(5): 1341-1347)
[18]	Sang H F, Liu F. Defocused palmprint recognition using 2DPCA. In: Proceedings of the 2009 International Conference on Artificial Intelligence and Computational Intelligence. Shanghai, China: IEEE, 2009. 611-615
[19]	Chan T, Wang C. Total variation blind deconvolution. IEEE Transactions on Image Processing, 1998, 7(3): 370-375
[20]	Vese L A, Osher S J. Modeling textures with total variation minimization and oscillating patterns in image processing. Journal of Scientific Computing, 2003, 19(1-3): 553-572
[21]	Terrence C, Wotao Y, Xiang S Z, Dorin C, Thomas S H. Total variation models for variable lighting face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(9): 1519-1524
[22]	Tao Shu-Ping, Zhang Xu-Yan, Jin Guang, Qu Hong-Song, Zheng Liang-Liang. Improvement of the definition evaluation function for TDI CCD remote sensing images by directional wavelet power spectrum. Infrared and Laser Engineering, 2013, 42(8): 2080-2084(陶淑平, 张续严, 金光, 曲宏松, 郑亮亮. 基于方向WPS改进TDI CCD遥感图像清晰度评价函数. 红外与激光工程, 2013, 42(8): 2080-2084)
[23]	Wang Z, Bovik A C, Sheikh H R, Simoncelli E P. Image quality assessment: from error visibility to structural similarity. IEEE Transaction on Image Processing, 2004, 13(4): 600-612
[24]	Guo Z H, Zhang L, Zhang D. A completed modeling of local binary pattern operator for texture classification. IEEE Transactions on Image Processing, 2010, 19(6): 1657-1663
[25]	Guo Xiu-Mei, Zhou Wei-Dong, Geng Shu-Juan, Wang Yu. A palmprint recognition algorithm based on horizontally expanded blanket dimension. Acta Automatica Sinica, 2012, 38(9): 1496-1502(郭秀梅, 周卫东, 耿淑娟, 王玉. 基于水平扩张毯子维的掌纹识别. 自动化学报, 2012, 38(9): 1496-1502)

施引文献

资源附件(0)

访问统计

计量

文章访问数: 1943
HTML全文浏览量: 107
PDF下载量: 1028
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

基于区域特征映射的模糊掌纹识别方法

doi: 10.16383/j.aas.2015.c131189

作者简介:
洪丹枫青岛大学信息工程学院硕士研究生. 主要研究方向为图像处理, 生物特征识别, 计算机视觉.E-mail: hongdanfeng1989@gmail.com

通讯作者:
魏伟波青岛大学信息工程学院副教授.2006 年获得南京理工大学工学博士学位. 主要研究方向为生物特征识别, 数字图像处理, 目标自动识别与跟踪. 本文通信作者. E-mail: njustwwb@163.com

计量

Blurred Palmprint Recognition Algorithm Based on Region Feature Map

计量

目录

留言板

基于区域特征映射的模糊掌纹识别方法

doi: 10.16383/j.aas.2015.c131189

作者简介: 洪丹枫 青岛大学信息工程学院硕士研究生. 主要研究方向为图像处理, 生物特征识别, 计算机视觉.E-mail: hongdanfeng1989@gmail.com

通讯作者: 魏伟波 青岛大学信息工程学院副教授.2006 年获得南京理工大学工学博士学位. 主要研究方向为生物特征识别, 数字图像处理, 目标自动识别与跟踪. 本文通信作者. E-mail: njustwwb@163.com

计量

出版历程

Blurred Palmprint Recognition Algorithm Based on Region Feature Map

计量

出版历程

目录

作者简介:
洪丹枫青岛大学信息工程学院硕士研究生. 主要研究方向为图像处理, 生物特征识别, 计算机视觉.E-mail: hongdanfeng1989@gmail.com

通讯作者:
魏伟波青岛大学信息工程学院副教授.2006 年获得南京理工大学工学博士学位. 主要研究方向为生物特征识别, 数字图像处理, 目标自动识别与跟踪. 本文通信作者. E-mail: njustwwb@163.com