非接触指纹图像识别算法研究

doi:10.3969/j.issn.0372-2112.2017.11.009

电子学报 ›› 2017, Vol. 45 ›› Issue (11): 2633-2640.DOI: 10.3969/j.issn.0372-2112.2017.11.009

非接触指纹图像识别算法研究

王科俊, 邢向磊, 崔会涛, 曹逸, 乔文亚, 徐怡博

哈尔滨工程大学自动化学院, 黑龙江哈尔滨 150001

收稿日期:2016-06-11 修回日期:2016-12-01 出版日期:2017-11-25
- 通讯作者:
- 邢向磊
- 作者简介:
- 王科俊,男,1962年生,教授,博士生导师,哈尔滨工程大学自动化学院模式识别与智能系统学科带头人.主要研究方向为模糊混沌神经网络、自适应逆控制理论、可拓控制、网络智能控制、模式识别、多模态生物特征识别、联脱机指纹考试身份鉴别系统、微小型机器人系统等.
- 基金资助:
- 国家自然科学基金面上项目 (No.61573114）; 黑龙江省自然科学基金面上项目 (No.F2015033）; 中央高校基本科研基金 (No.HEUCFJ170404）

Recognition Algorithm Research of the Touchless Fingerprint Images

WANG Ke-jun, XING Xiang-lei, CUI Hui-tao, CAO Yi, QIAO Wen-ya, XU Yi-bo

College of Automation, Harbin Engineering University, Harbin, Heilongjiang 150001, China

Received:2016-06-11 Revised:2016-12-01 Online:2017-11-25 Published:2017-11-25
- Supported by:
- National Natural Science Foundation of China (No.61573114); General Program of Natural Science Foundation of Heilongjiang Province, China (No.F2015033); Fundamental Research Funds for the Central Universities (No.HEUCFJ170404)

摘要/Abstract

摘要： 非接触指纹识别具有接受程度高、防伪性高、卫生性高等优点，是目前生物特征识别领域的研究热点，但是非接触指纹图像的背景区域比接触式的相对复杂，指纹图像会出现旋转和平移现象，且脊、谷线的对比度较低，这些因素严重影响了非接触指纹的识别性能.采用接触式指纹图像处理方法很难达到良好的处理效果.本文根据非接触指纹图像的特点提出了相应的非接触指纹图像的预处理方法.首先采用图像YCbCr模型中的Cb分量和Otsu法相结合的方法进行手指区域的提取.其次采用高频强调滤波和迭代自适应直方图均衡化相结合的图像增强算法进行图像增强处理，再用简化的Gabor函数模板进行二次增强，然后提出了一种手指指纹ROI区域提取的方法.最后本文采用基于AR-LBP算法进行特征提取，利用最近邻分类器进行特征匹配.实验结果表明，本文提出的非接触指纹算法能够达到很好的图像识别效果.

关键词: 非接触指纹, 高频强调滤波, Otsu, 自适应直方图均衡化, ROI区域, AR-LBP算法

Abstract: Touchless fingerprint recognition with high acceptance,high security,hygiene advantages,is currently a hot research field of biometrics,The background areas of touchless fingerprints are more complex than those of the contact,Fingerprint image will appear rotation and translation phenomenon,What's more,the contrast of the ridge and valley lines is much lower,These factors seriously affected the performance of the touchless fingerprint recognition.So the general methods for contact fingerprint images are difficult to achieve good effect.Firstly,In this paper,a method is put out to preprocess the images reasonably aiming at these features.Secondly,the Otsu based on the Cb component of the YCbCr model is adopted to extract the finger area.When the fingerprint images are enhanced,combining the high frequency emphasis filtering and iterative adaptive histogram equalization technique is adopted firstly and then the simplified Gabor function template is used to enhance them again.thirdly,this paper proposed a new method of extracting the ROI fingerprint area.lastly,AR-LBP algorithm is adopted for feature extraction and the nearest neighbor classifier is used for feature matching.Experimental results show that the proposed method in this paper can achieve good image identify results.

Key words: touchless fingerprint, high frequency emphasis filtering, Otsu, adaptive histogram equalization, ROI area, AR-LBP algorithm

中图分类号:

TN911.23

王科俊, 邢向磊, 崔会涛, 等. 非接触指纹图像识别算法研究[J]. 电子学报, 2017, 45(11): 2633-2640.

WANG Ke-jun, XING Xiang-lei, CUI Hui-tao, et al. Recognition Algorithm Research of the Touchless Fingerprint Images[J]. Acta Electronica Sinica, 2017, 45(11): 2633-2640.

参考文献

[1] 陈继延.自动指纹识别技术的发展与应用[J].计算机光盘软件与应用,2013,16(9):56-57.
[2] 解梅,佟异.基于脊线采样的指纹识别算法[J].电子学报,2003,31(10):1503-1505. Xie Mei,Tong Yi.A fingerprint identification algorithm based on ridge-sampling[J].Acta Electronica Sinica,2003,31(10):1503-1505.(in Chinese)
[3] Parziale G,Diaz-Santana E,Hauke R.The surround imagertm:A Multi-Camera Touchless Device to Acquire 3d Rolled-Equivalent Fingerprints[M].Berlin Heidelberg Biometrics,Springer,2005.244-250.
[4] Labati R D,Genovese A,and Piuri V,et al.Quality measurement of unwrapped three-dimensional fingerprints:a neural networks approach[A] Neural Networks (IJCNN),The 2012 International Joint Conference on[C].IEEE,2012.1-8.
[5] 李永,殷建平,祝恩,等.动态分数选择的多视角非接触指纹识别融合[J].哈尔滨工业大学学报,2012,44(7):108-113. Li Yong,Yin Jianping,Zhu En,et al.Dynamic score selection for multi-vision touchless fingerprint recognition fusion[J].Journal of Harbin Institute of Technology,2012,44(7):108-113.(in Chinese)
[6] Choi H,Choi K,Kim J.Mosaicing touchless and mirror-reflected fingerprint images[J].IEEE Translations on Information Forensics and Security,2010,5(1):52-61.
[7] Piuri V,Scotti F.Fingerprint biometrics via low-cost sensors and webcams[A].2nd IEEE International Conference on Biometrics:Theory,Applications and Systems,BTAS 2008[C].IEEE,2008.1-6
[8] Derawi M O,Yang B,Busch C.Fingerprint Recognition with Embedded Cameras on Mobile Phones[M].Security and Privacy in Mobile Information and Communication Systems.Springer Berlin Heidelberg,2012.136-147.
[9] Kumar A,Kwong C.Towards contactless,low-cost and accurate 3D fingerprint identification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(3):681-696.
[10] Assogba M K,Ali A N.Fingerprint characteristic extraction by ridge orientation:An approach for a supervised contactless biometric system[J].International Journal of Computer Applications,2011,16(6):22-35.
[11] 张雄,贺贵明.一种指纹宏观曲率特征提取算法[J].电子学报,2002,30(11):1722-1725. Zhang Xiong,He Guiming.An algorithm to extract the macroscopic curvature feature of fingerprint[J].Acta Electronica Sinica,2002,31(11):1722-1725.(in Chinese)
[12] Kaur P,Jain A,Mittal S.Touch-less fingerprint analysis-a review and comparison[J].International Journal of Intelligent Systems and Applications (IJISA),2012,4(6):46.
[13] Hiew B Y,Teoh A B J,Ngo D C L.Automatic digital camera based fingerprint image preprocessing[A].International Conference on Computer Graphics,Imaging and Visualisation,2006[C].IEEE,2006.182-189.
[14] Labati R D,Genovese A,Piuri V,et al.Contactless fingerprint recognition:a neural approach for perspective and rotation effects reduction[A].2013 IEEE Workshop on Computational Intelligence in Biometrics and Identity Management (CIBIM)[C].IEEE,2013.22-30.
[15] 秦芬芬,廖斌.非接触指纹图像分割与增强方法的研究[J].传感器世界,2014,(8):16-19. Cai Fenfen,Liao Bin.Research on touchless fingerprint image segmentation and enhancement[J].Sensor World,2014,(8):16-19.(in Chinese)
[16] Angelopoulou E.Understanding the color of human skin[A].Photonics West 2001-Electronic Imaging[C].International Society for Optics and Photonics,2001.243-251.
[17] Naika C L S,Das P K,Nair S B.Asymmetric region Local Binary Pattern operator for person-dependent facial expression recognition[A].2012 International Conference on Computing,Communication and Applications (ICCCA)[C].IEEE,2012.1-5.
[18] 谢凤英,赵丹培等.Visual C ++数字图像处理[M].北京:电子工业出版社,2008,285-288.
[19] 周卫星,廖欢.基于高频强调滤波和CLAHE的雾天图像增强方法[J].电视技术,2010,(7):38-40.
[20] 宋刚,刘瑶华.一种能强化细节的自适应直方图均衡法[J].山东工业大学学报,1999,29(1):81-85. Song Gang,Liu Yaohua.A self-adaptive histogram equalization method for detail enhancement[J].Journal of Shandong University of Technology,1999,29(1):81-85.(in Chinese)
[21] 马慧,王科俊.采用旋转校正的指静脉图像感兴趣区域提取方法[J].智能系统学报,2012,7(3):230-234. Ma Hui,Wang Kejun.A region of interest extraction method using rotation rectified finger vein images[J].CAAI Transactions on Intelligent Systems,2012,7(3):230-234.(in Chinese)
[22] 孙冬梅,裘正定.生物特征识别技术综述[J].电子学报,2001,29(S1):1744-1748. Sun Dongmei,Qiu Zhengding.A survey of biometrics[J].Acta Electronica Sinica,2001,29(S1):1744-1748.(in Chinese)

非接触指纹图像识别算法研究

Recognition Algorithm Research of the Touchless Fingerprint Images

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

[1]	何志勇, 孙立宁, 陈立国. Otsu准则下分割阈值的快速计算[J]. 电子学报, 2013, 41(2): 267-272.
[2]	吴成茂. 基于后验概率熵的正则化Otsu阈值法[J]. 电子学报, 2013, 41(12): 2474-2478.
[3]	张新明;孙印杰;郑延斌. 二维直方图准分的Otsu图像分割及其快速实现[J]. 电子学报, 2011, 39(8): 1778-1784.
[4]	申铉京;龙建武;陈海鹏;魏巍(吉林大学符号计算与知识工程教育部重点实验室;吉林长春00). 三维直方图重建和降维的Otsu阈值分割算法[J]. 电子学报, 2011, 39(5): 1108-1114.
[5]	范九伦;雷博. 灰度图像的二维交叉熵直线型阈值分割法[J]. 电子学报, 2009, 37(3): 476-480.
[6]	许向阳;宋恩民;金良海;. Otsu准则的阈值性质分析[J]. 电子学报, 2009, 37(12): 2716-2719.
[7]	范九伦, 赵凤, 张雪峰, . 三维Otsu阈值分割方法的递推算法[J]. 电子学报, 2007, 35(7): 1398-1402.
[8]	范九伦, 赵凤. 灰度图像的二维Otsu曲线阈值分割法[J]. 电子学报, 2007, 35(4): 751-755.