虹膜识别算法的研究
|
摘要
生物特征识别技术是一种新兴的身份识别技术,由于其具有很高的安全性与防伪性等特点,目前越来越受到广大科研工作者们的关注。在众多生物特征识别技术之中,虹膜识别技术由于具有高度的防伪性、唯一性、稳定性、可采集性以及非侵犯性等特点,被认为是一种极具研究价值与应用前景的生物特征识别技术。本文首先介绍了生物特征识别技术的背景知识以及现有的几种生物特征识别技术,并对它们的特点进行了比较;然后详细介绍了虹膜识别技术及虹膜识别系统的构成;并对虹膜识别的算法进行研究,提出了一种基于Gabor滤波器提取局部纹理特征的虹膜识别算法,并在CASIA数据库中进行了相关实验。虹膜识别算法包括虹膜图像的定位、归一化及特征提取与匹配,在本文中对每个步骤都进行了研究,主要工作内容如下:
1.研究了一种基于最小方差搜索圆心的快速虹膜定位算法。该算法首先利用区域生长法消除亮斑的干扰;然后利用虹膜的灰度分布特征采用投影法粗略得到虹膜的内边缘圆周参数;最后利用Canny算子、先验知识以及内边缘圆周参数,采用设计的算法得到虹膜外边缘圆周参数;
2.运用Daugman的橡皮纸模型法归一化虹膜图像,得到虹膜的矩形图像,使虹膜图像具有平移、缩放不变性;再对虹膜归一化图像进行图像增强以提高虹膜纹理的对比度;最后确定虹膜图像的有效区域以减少眼睑及眼睫毛等噪声对虹膜纹理的影响;
3.研究了一种基于Gabor滤波器提取局部纹理特征的虹膜特征提取算法。该算法是将滤波器滤波输出图像的滤波系数的绝对值函数作为权值,对滤波图像所有像素点进行加权平均,从而确定虹膜特征点,并设计了一种较优加权的方法,使滤波系数大的对特征点贡献大,滤波系数小的对特征点贡献小。最后利用设计的欧式距离分类器对虹膜特征点进行分类匹配。
将本文设计的算法在中科院自动化研究所提供的CASIA虹膜数据库子库中进行实验,实验结果表明,该算法具有很高的识别率,识别率达到99.77%,并且该算法对虹膜的旋转具有相对稳定性。
Biometrics is a new identification technology, because of its high safety and security, now it is concerned by more and more scientists. As one of the biometrics, iris recognition technology has the characteristics of high security, uniqueness, stability, availability of acquisition and non-invasiveness, and is regard as a technology of great research value and wide application prospects.
In this paper, the background of biometrics and several existing biometrics are introduced firstly, and their characteristics are compared; then the iris recognition technology and the iris recognition system are discussed in details; finally, the algorithm of iris recognition is studied, and an algorithm of the iris local texture feature extraction based on Gabor filter is proposed, and the relevant experiments are carried out in the CASIA iris database. Iris recognition algorithm mainly comprises image positioning, normalization, feature extraction and match. This paper makes studies on all these parts, and the main jobs are as follows:
1. A fast iris location algorithm based on minimal variance searching center is studied. Firstly, the region growing method is applied in the algorithm to eliminate the interference of bright spots; then based on the gray distribution features of iris, projection method is applied to get the circle parameters of iris’inner edge; lastly, the circle parameters of iris’outer edge is obtained by applying the Canny operator, the prior knowledge, the designed algorithm using the circle parameters of inner edge.
2. The iris image is normalized by applying Daugman’s rubber paper model method, and the rectangular image of iris with the feature of translation and scale invariance is gained. Then the normalized iris image is enhanced to improve the contrast of the iris texture. Finally, the effective area of iris is determined to reduce the impact of eyelids and eyelashes on iris texture.
3. An iris feature extraction algorithm which extracts the local texture feature based on the Gabor filter is studied. The algorithm makes the absolute value of the output image’s filter coefficients as a weight, then operates weight average on all the pixels of the filtered image and gets the feature points of iris. In the process, an optimal weighting method is proposed. It makes the bigger filter coefficients greater contribution to feature points and the smaller filter coefficients less. Finally, the Euclidean distance classifier is designed to classify the feature points.
The algorithms designed in this paper are applied to the sub CASIA iris database which is provided by Institute of Automation, Chinese Academy of Sciences, and the results show that the algorithm have a higher recognition rate which is up to 99.77%, and it is relative stable for the rotation of iris.
1.研究了一种基于最小方差搜索圆心的快速虹膜定位算法。该算法首先利用区域生长法消除亮斑的干扰;然后利用虹膜的灰度分布特征采用投影法粗略得到虹膜的内边缘圆周参数;最后利用Canny算子、先验知识以及内边缘圆周参数,采用设计的算法得到虹膜外边缘圆周参数;
2.运用Daugman的橡皮纸模型法归一化虹膜图像,得到虹膜的矩形图像,使虹膜图像具有平移、缩放不变性;再对虹膜归一化图像进行图像增强以提高虹膜纹理的对比度;最后确定虹膜图像的有效区域以减少眼睑及眼睫毛等噪声对虹膜纹理的影响;
3.研究了一种基于Gabor滤波器提取局部纹理特征的虹膜特征提取算法。该算法是将滤波器滤波输出图像的滤波系数的绝对值函数作为权值,对滤波图像所有像素点进行加权平均,从而确定虹膜特征点,并设计了一种较优加权的方法,使滤波系数大的对特征点贡献大,滤波系数小的对特征点贡献小。最后利用设计的欧式距离分类器对虹膜特征点进行分类匹配。
将本文设计的算法在中科院自动化研究所提供的CASIA虹膜数据库子库中进行实验,实验结果表明,该算法具有很高的识别率,识别率达到99.77%,并且该算法对虹膜的旋转具有相对稳定性。
Biometrics is a new identification technology, because of its high safety and security, now it is concerned by more and more scientists. As one of the biometrics, iris recognition technology has the characteristics of high security, uniqueness, stability, availability of acquisition and non-invasiveness, and is regard as a technology of great research value and wide application prospects.
In this paper, the background of biometrics and several existing biometrics are introduced firstly, and their characteristics are compared; then the iris recognition technology and the iris recognition system are discussed in details; finally, the algorithm of iris recognition is studied, and an algorithm of the iris local texture feature extraction based on Gabor filter is proposed, and the relevant experiments are carried out in the CASIA iris database. Iris recognition algorithm mainly comprises image positioning, normalization, feature extraction and match. This paper makes studies on all these parts, and the main jobs are as follows:
1. A fast iris location algorithm based on minimal variance searching center is studied. Firstly, the region growing method is applied in the algorithm to eliminate the interference of bright spots; then based on the gray distribution features of iris, projection method is applied to get the circle parameters of iris’inner edge; lastly, the circle parameters of iris’outer edge is obtained by applying the Canny operator, the prior knowledge, the designed algorithm using the circle parameters of inner edge.
2. The iris image is normalized by applying Daugman’s rubber paper model method, and the rectangular image of iris with the feature of translation and scale invariance is gained. Then the normalized iris image is enhanced to improve the contrast of the iris texture. Finally, the effective area of iris is determined to reduce the impact of eyelids and eyelashes on iris texture.
3. An iris feature extraction algorithm which extracts the local texture feature based on the Gabor filter is studied. The algorithm makes the absolute value of the output image’s filter coefficients as a weight, then operates weight average on all the pixels of the filtered image and gets the feature points of iris. In the process, an optimal weighting method is proposed. It makes the bigger filter coefficients greater contribution to feature points and the smaller filter coefficients less. Finally, the Euclidean distance classifier is designed to classify the feature points.
The algorithms designed in this paper are applied to the sub CASIA iris database which is provided by Institute of Automation, Chinese Academy of Sciences, and the results show that the algorithm have a higher recognition rate which is up to 99.77%, and it is relative stable for the rotation of iris.
引文
[1]卢官明,李海波,刘莉.生物特征识别综述[J].南京邮电大学学报,2007, 27(1):81-88.
[2] Prins C. Biometric technology law [J]. Computer Law and Security Reports, 1998, 14(3): 159-165.
[3] Shen W, Marc S, Rajiv K, Evaluation of Automated Biometrics-based Identification and Verification System [J]. Proceedings of the IEEE, 1997, 85(9): 1464-1478.
[4]杨艳.生物特征识别技术概述[EB/OL]. http://www.lunwennet.com/thesis/2007/16214.html.
[5]尤鸿霞.虹膜识别技术的算法研究[D].无锡:江南大学, 2006. 5-6.
[6] Daugman J G, Downing C. Epigenetic randomness, complexity and singularity of human iris patterns. The Royal Society, 2001, 268:1737-1740.
[7] Daugman J G. High confidence personal identification by rapid video analysis of iris texture. In Proceedings of IEEE 1992 International Carnahan Conference on Security Technology, Tainan, Taiwan, china, 1992, 50-60.
[8]徐霞.虹膜识别若干关键问题研究[D].沈阳:沈阳工业大学, 2008. 16-17.
[9]孙哲男,谭铁牛.虹膜识别研究与应用综述[J].综述·Attention, 2005(02): 25-26.
[10] Flom L and Safir A. Iris Recognition System. US: Patent 4641349, 1987.
[11] Wildes R.P. Automated, Non-invasive Iris Recognition System and Method. US: Patent 5572596, 1996.
[12]吴惠敏,郑晓势,赵彦玲.虹膜识别技术综述[J].大众科技, 2008(01): 41-43.
[13] Sergios Theodoridis.模式识别(第4版)[M].北京:电子工业出版社, 2006,51-51.
[14] Daugman J G. Recognizing People by their Iris Pattern [J]. Information Security Technical Report, 1998, 3(1): 33-39.
[15] Wildes R P, Asmuth J C. Iris Recognition: An Emerging Biometric Technology [J]. Proceedings of the IEEE, 1997, 85(9): 1348-1363.
[16]谭铁牛,朱勇,王蕴红.虹膜图像采集装置[P].中国专利,实用新型, ZL 99217063.X.2005.
[17]中科院自动化研究所,CASIA虹膜图像数据库(版本1.0),http://www.sinobiometrics.com.
[18] Daugman J G. High confidence visual recognition of persons by a test of statistical independence. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(1): 1148-1161.
[19]郭永彩,徐梅宣,高潮.一种快速虹膜定位算法[J].光电工程, 2005, 32(7): 33-36.
[20]苑玮琦,马军防,狄文彬.基于主动轮廓线的虹膜定位算法[J].计算机工程与应用, 2003(34): 104-107.
[21]吴建华,邹德凯,李静辉.基于小范围搜索的虹膜定位算法[J].仪器仪表学报, 2008, 29(8): 1704-1708.
[22]王洪,曾文.一种改进的虹膜定位算法研究[J].武汉理工大学学报, 2008, 30(6): 846-848.
[23]杜德生,高雪莲,张格森.一种新的快速虹膜定位算法[J].微计算机信息, 2009, 7(2): 207-209.
[24]马争,黄祎.曲线拟合的虹膜定位算法研究[J].电子科技大学学报, 2009, 38(3): 426-430.
[25] N. Otsu. Threshold Selection Method from Gray-level Histograms [J]. IEEE Transactions on Systems, Man and Cybernetics, 1979, SMC-9(1):62-66.
[26] Gonzalez Rafael C. Digital image processing [M]. Beijing: Publishing house of electronics industry, 2006: 519-530.
[27]李清华.虹膜定位算法研究[D].重庆:重庆大学,2006.
[28] CANNY J A. Computional approach to edge detection [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
[29]潘力立.虹膜识别算法的研究及实现[D].成都:电子科技大学,2007,47-48.
[30] Daugman J G. Biometrical Personal Identification System Based on Iris Analysis, US: Patent 52911560, 1994.
[31]冈萨雷斯.数字图像处理(第二版)[M].北京:电子工业出版. 2005.
[32]章毓晋.图像工程(下册)-图像理解与计算机视觉[M].北京:清华大学出版社,1999.
[33]王蕴红,朱勇,谭铁牛.基于虹膜的身份鉴别[J].自动化学报,2002,28(1):1-10.
[34] Boles W W, Boashash. A human identification technique using images of the iris and wavelet transform [J]. IEEE Trans on Signal Processing, 1998, 46(4): 1185-1188.
[35] Boles W W. A Security System Based on Human Iris Identification Using Wavelet Transform [J]. Engineering Applications of Artificial Intelligence, 1998, 11: 77-85.
[36]苑玮琦,冯琪,柯丽.利用2D-Gabor滤波器提取纹理方向特征的虹膜识别算法[J]. 2009, 26(8): 3166-3168.
[37]谷建清,郭永彩,高潮.二维Gabor小波在虹膜识别中的应用[J]. 2005, 26(8): 385-397.
[38]郭永彩,谷建清,高潮.用Gabor滤波实现虹膜图像的纹理编码[J]. 2006, 33(4): 35-38.
[39]苑玮琦,刘汪澜,柯丽.用于虹膜特征提取的Gabor滤波器参数选取方法的研究[J]. 2008, 19(9):1235-1239.
[40]田启川,潘泉,程咏梅.基于过零检测的虹膜特征提取算法[J]. 2006, 28(8): 1452-1457.
[41] Ma L, Wang Y, Tan T. Iris Recognition Based on Multi-channel Gabor Filtering [J]. Proceedings of ACCV 2002, 1: 279-283.
[42] Ma L, Wang Y, Tan T. Iris Recognition Using Circular Symmetric Filters [J]. The Sixteenth International Conference on Pattern Recognition, 2002, 2: 414-417.
[43] Ma L, Wang Y, Tan T. Personal Identification Based on Iris Texture Analysis [J]. IEEETransactions on Pattern Analysis and Machine Intelligence, 2003, 25(12): 1519-1533.
[44] Gabor D. Theory of Communication [J]. J Inst Elect Eng, 1946, 93: 429-457.
[45] Daugman J G. Complete Discrete 2-D Gabor Transforms by Neural Networks of image Analysis and Compression [J]. IEEE Trans on Acoustics Speech & Signal Proceeding, 1998, 36(7): 1169-1179.
[46] Daugman J G. How iris recognition works [J]. IEEE Transaction on Circuits and Systems for Video Technology, 2004, 14(1): 21-30.
[47] Daugman J G. Demodulation by complex-valued wavelets for stochastic pattern recognition. International Journal of Wavelets, Multi-resolution and Information Processing, 2003, 1(1):1-17.
[48] Daugman J G. Recognising persons by their iris patterns. In Proceedings of the 2004 Chinese Conference on Biometric Recognition, Guangzhou, China, December 13-14, 2004, LNCS 3338: 5-25.
[49] Li Ma, Tieniu Tan, Yunhong Wang. Local intensity variation analysis for iris recognition . Pattern Recognition 2004, 37: 1287-1298.
[2] Prins C. Biometric technology law [J]. Computer Law and Security Reports, 1998, 14(3): 159-165.
[3] Shen W, Marc S, Rajiv K, Evaluation of Automated Biometrics-based Identification and Verification System [J]. Proceedings of the IEEE, 1997, 85(9): 1464-1478.
[4]杨艳.生物特征识别技术概述[EB/OL]. http://www.lunwennet.com/thesis/2007/16214.html.
[5]尤鸿霞.虹膜识别技术的算法研究[D].无锡:江南大学, 2006. 5-6.
[6] Daugman J G, Downing C. Epigenetic randomness, complexity and singularity of human iris patterns. The Royal Society, 2001, 268:1737-1740.
[7] Daugman J G. High confidence personal identification by rapid video analysis of iris texture. In Proceedings of IEEE 1992 International Carnahan Conference on Security Technology, Tainan, Taiwan, china, 1992, 50-60.
[8]徐霞.虹膜识别若干关键问题研究[D].沈阳:沈阳工业大学, 2008. 16-17.
[9]孙哲男,谭铁牛.虹膜识别研究与应用综述[J].综述·Attention, 2005(02): 25-26.
[10] Flom L and Safir A. Iris Recognition System. US: Patent 4641349, 1987.
[11] Wildes R.P. Automated, Non-invasive Iris Recognition System and Method. US: Patent 5572596, 1996.
[12]吴惠敏,郑晓势,赵彦玲.虹膜识别技术综述[J].大众科技, 2008(01): 41-43.
[13] Sergios Theodoridis.模式识别(第4版)[M].北京:电子工业出版社, 2006,51-51.
[14] Daugman J G. Recognizing People by their Iris Pattern [J]. Information Security Technical Report, 1998, 3(1): 33-39.
[15] Wildes R P, Asmuth J C. Iris Recognition: An Emerging Biometric Technology [J]. Proceedings of the IEEE, 1997, 85(9): 1348-1363.
[16]谭铁牛,朱勇,王蕴红.虹膜图像采集装置[P].中国专利,实用新型, ZL 99217063.X.2005.
[17]中科院自动化研究所,CASIA虹膜图像数据库(版本1.0),http://www.sinobiometrics.com.
[18] Daugman J G. High confidence visual recognition of persons by a test of statistical independence. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(1): 1148-1161.
[19]郭永彩,徐梅宣,高潮.一种快速虹膜定位算法[J].光电工程, 2005, 32(7): 33-36.
[20]苑玮琦,马军防,狄文彬.基于主动轮廓线的虹膜定位算法[J].计算机工程与应用, 2003(34): 104-107.
[21]吴建华,邹德凯,李静辉.基于小范围搜索的虹膜定位算法[J].仪器仪表学报, 2008, 29(8): 1704-1708.
[22]王洪,曾文.一种改进的虹膜定位算法研究[J].武汉理工大学学报, 2008, 30(6): 846-848.
[23]杜德生,高雪莲,张格森.一种新的快速虹膜定位算法[J].微计算机信息, 2009, 7(2): 207-209.
[24]马争,黄祎.曲线拟合的虹膜定位算法研究[J].电子科技大学学报, 2009, 38(3): 426-430.
[25] N. Otsu. Threshold Selection Method from Gray-level Histograms [J]. IEEE Transactions on Systems, Man and Cybernetics, 1979, SMC-9(1):62-66.
[26] Gonzalez Rafael C. Digital image processing [M]. Beijing: Publishing house of electronics industry, 2006: 519-530.
[27]李清华.虹膜定位算法研究[D].重庆:重庆大学,2006.
[28] CANNY J A. Computional approach to edge detection [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
[29]潘力立.虹膜识别算法的研究及实现[D].成都:电子科技大学,2007,47-48.
[30] Daugman J G. Biometrical Personal Identification System Based on Iris Analysis, US: Patent 52911560, 1994.
[31]冈萨雷斯.数字图像处理(第二版)[M].北京:电子工业出版. 2005.
[32]章毓晋.图像工程(下册)-图像理解与计算机视觉[M].北京:清华大学出版社,1999.
[33]王蕴红,朱勇,谭铁牛.基于虹膜的身份鉴别[J].自动化学报,2002,28(1):1-10.
[34] Boles W W, Boashash. A human identification technique using images of the iris and wavelet transform [J]. IEEE Trans on Signal Processing, 1998, 46(4): 1185-1188.
[35] Boles W W. A Security System Based on Human Iris Identification Using Wavelet Transform [J]. Engineering Applications of Artificial Intelligence, 1998, 11: 77-85.
[36]苑玮琦,冯琪,柯丽.利用2D-Gabor滤波器提取纹理方向特征的虹膜识别算法[J]. 2009, 26(8): 3166-3168.
[37]谷建清,郭永彩,高潮.二维Gabor小波在虹膜识别中的应用[J]. 2005, 26(8): 385-397.
[38]郭永彩,谷建清,高潮.用Gabor滤波实现虹膜图像的纹理编码[J]. 2006, 33(4): 35-38.
[39]苑玮琦,刘汪澜,柯丽.用于虹膜特征提取的Gabor滤波器参数选取方法的研究[J]. 2008, 19(9):1235-1239.
[40]田启川,潘泉,程咏梅.基于过零检测的虹膜特征提取算法[J]. 2006, 28(8): 1452-1457.
[41] Ma L, Wang Y, Tan T. Iris Recognition Based on Multi-channel Gabor Filtering [J]. Proceedings of ACCV 2002, 1: 279-283.
[42] Ma L, Wang Y, Tan T. Iris Recognition Using Circular Symmetric Filters [J]. The Sixteenth International Conference on Pattern Recognition, 2002, 2: 414-417.
[43] Ma L, Wang Y, Tan T. Personal Identification Based on Iris Texture Analysis [J]. IEEETransactions on Pattern Analysis and Machine Intelligence, 2003, 25(12): 1519-1533.
[44] Gabor D. Theory of Communication [J]. J Inst Elect Eng, 1946, 93: 429-457.
[45] Daugman J G. Complete Discrete 2-D Gabor Transforms by Neural Networks of image Analysis and Compression [J]. IEEE Trans on Acoustics Speech & Signal Proceeding, 1998, 36(7): 1169-1179.
[46] Daugman J G. How iris recognition works [J]. IEEE Transaction on Circuits and Systems for Video Technology, 2004, 14(1): 21-30.
[47] Daugman J G. Demodulation by complex-valued wavelets for stochastic pattern recognition. International Journal of Wavelets, Multi-resolution and Information Processing, 2003, 1(1):1-17.
[48] Daugman J G. Recognising persons by their iris patterns. In Proceedings of the 2004 Chinese Conference on Biometric Recognition, Guangzhou, China, December 13-14, 2004, LNCS 3338: 5-25.
[49] Li Ma, Tieniu Tan, Yunhong Wang. Local intensity variation analysis for iris recognition . Pattern Recognition 2004, 37: 1287-1298.