摘要
手掌静脉图像是一种生物特征识别技术,在识别过程中具有活体识别、内部特征、非接触式、不可伪造性等优点,成为身份认证的研究热点。但是,手掌静脉在获取和传输过程中,通常会出现噪声附加以及图像失真等问题,为了给手掌静脉识别系统提供可靠的特征依据,需要对采集到的手掌静脉图像进行增强和降噪处理。
Contourlet变换作为一种新的多尺度分析方法,不但具有多分辨率时频分析特性,而且具有良好的各向异性和方向选择性,能够用较少的系数来表示光滑的曲线,是一种“真正”的二维图像稀疏表示方法。本文围绕Contourlet变换在手掌静脉图像降噪和增强中的应用进行研究,主要工作如下:
(1)详细介绍了Contourlet变换和非下采样Contourlet变换的基本原理,为后续降噪和增强算法的研究奠定了基础。(2)分析了噪声对手掌静脉图像的影响,针对传统Contourlet阈值降噪方
法中存在的“过扼杀”现象,提出一种基于Contourlet变换的手掌静脉图像去噪算法。对分解系数作尺度积,使系数具有较强的相关性,根据各尺度不同方向子带的能量分布确定阈值,在近似分量和细节分量上分别采用S型函数和收缩阈值函数对系数进行处理,从而在降噪的同时避免了过度的扼杀边缘信息的现象。实验结果表明本算法去噪效果良好。
(3)分析了手掌静脉图像质量分布不均的问题,针对图像进行局部直方图均衡化处理后出现的局部区域过度模糊、噪声附加等问题,采用自适应窗口的方法改进了均衡化算法;并将该算法应用到非下采样Contourlet变换增强算法中,在增强图像的同时抑制噪声;最后通过Gabor滤波器增强手掌静脉纹路信息。实验结果表明本算法增强效果比较明显。
Palm vein image as a cutting-edge technology of biometric trick identification, it has the characteristics of trueprint, non-contact and unforgeability during the identification, so it becomes the research hotspot of authentication. But the problems of the noise and image error often appear in the process of the acquisition and transmission for palm vein. In order to provide the credible characteristic basis for the system of palm vein identification, it is necessary to enhance the collected images of palm vein and implement the noise reduction.
Contourlet transformation as a new multi-scale analysis method, it not only has the multi-resolution and time-frequency analysis features, but also has good anisotropy and directional selectivity, and it can express the smooth curve with less coefficients, which is a true of sparse representation of two-dimensional images. This paper revolves around Contourlet transformation in the application of noise reduction and enhancement for palm vein image. The main tasks are as follows:
(1) Described the basic principle of Contourlet transformation and Contourlet transformation of non-down-sampling in detail, which lay the foundation for the next study of the noise reduction and enhancement algorithms.
(2) Analyze the noise of palm vein image. According to the "over kill" phenomenon of the traditional threshold denoising method, a noise reduction algorithm of palm vein image based on Contourlet transform is proposed. The shrinkage factor is used to distinct the information coefficient and noise coefficient in the approximate area. The semi-soft threshold is used to denoise in the detail weight of images. So the over-kill information phenomenon is avoided. The experimental results show that the algorithm has good effect of de-noising.
(3) Analyze the quality maldistribution of the palm vein image. Because the enforcement effect of the equalization algorithm of the traditional local histogram is not obvious, an improved algorithm of it is proposed. This algorithm is applied to the Contourlet transformation of non-down-sampling and an enhancement algorithm of palm vein image is proposed. At last, the lines of the palm vein are enhanced by Gabor filter. The experimental results show that the enhancement effect of this algorithm is more obvious.
引文
[1] Li Zeng, Rui Ma. The construction of 2D rotationally invariant wavelets and their application in image edge detection[J]. International Journal of Wavelets ,Multiresolution and Information Processing. 2008, 6(1):65-82.
[2] L. V. Novikov. Modified wavelets and their applications[J]. Journal of Communications Technology and Electronics. 2006, 51(11):1261-1270.
[3] P. Heinlein, W. Schneider. Integrated wavelets for medical image analysis[J]. Proceedings of SPIE - The International Society for Optical Engineering. 2003, 5207(455):455-466.
[4] M. N. Do, M. Vetterli. Contourlets: A new directional multiresolution image representation[C]. Conference Record of the Asilomar Conference on Signals, Systems and Computers. 2002, 1: 497-501.
[5] M. N. Do, M. Vetterli. The contourlet transform: An efficient directional multiresolution image representation[J]. IEEE Transactions on Image Processing. 2005, vol. 14:2091-2106.
[6] H. Zhu, Chan F.H.Y. Image contrast enhancement by constrained local histogram equalization[J]. Computer Vision and Image Understanding. 1999, 73(2):281-290.
[7] Doi. Masaaki Yamanaka. Personal Authentication Using Feature Points on Finger and Palmar Ceases[J]. Proceedings of the 32nd Applied Imagery Pattern Recognition Workshop. 2003:282-287.
[8] H. Ibrahim, N. S. P. Kong. Brightness preserving dynamic histogram equalization for image contrast enhancement[J]. IEEE Transactions on Consumer Electronics. 2007, 53(4):1752-1758.
[9] Wildes, Richard P. Iris recognition:an emerging biometric technology[J]. Proc IEEE. 1997, 85(9):136-142.
[10] H. Yoon. Image contrast enhancement based sub-histogram equalization technique without over-equalization noise[J]. Proceedings of World Academy of Science, Engineering and Technology. 2009, 38(50):176-182.
[11]赵建军,熊馨,张磊.基于CLAHE和top―hat变换的手背静脉图像增强算法[J].激光与红外.2009,39(2):20-222.
[12]郝伟.基于灰度变换的红外图像实时分割算法[J].光子学报.2008,37(5):1077-1080.
[13] R Chellappa. Human and machine recognition of face[J]. A survey Prc IEEE. 1995, 83(5):705-740.
[14] Y. Yan. Image denoising: An approach based on wavelet neural network and improved medianfiltering[R]. In 6th World Congress on Intelligent Control and Automation. 2006:10063-10067.
[15] R. Chellappa. Human and machine recognition of face[J]. A survey Prc IEEE. 1995, 83(5): 705-740.
[16] Z. Zhou. Image denoising algorithm based on adaptive windows in wavelet domain[J]. Systems Engineering and Electronics. 2007, 29(8):1238-1241.
[17] S. Zhang .Palmprint linear feature extraction and identification based on ridgelet transforms and rough sets[J] .Lecture Notes in Computer Science .2008 ,vol. 5227: 1101-1108.
[18] DaQi Zhang. Image enhancement algorithm on ridgelet domain in detection of road cracks[J]. China Journal of Highway and Transport. 2009, 22(2):26-30+76.
[19] J.-L. Starck. Gray and color image contrast enhancement by the curvelet transform[J]. IEEE Transactions on Image Processing. 2003, 12(6):706-717.
[20] G. Amayeh. Fingerprint images enhancement in curvelet domain[J]. Lecture Notes in Computer Science. 2008, 5359:541-550.
[21] E. Nezhadarya, M. B. Shamsollahi. Image contrast enhancement by contourlet transform[R]. International Symposium Electronics in Marine. 2006:81-84.
[22] P. Feng. Enhancing retinal image by the Contourlet transform[J]. Pattern Recognition Letters. 2007, 28(4):516-522.
[23] ZhiGang Chen, FuChang. Yin. Enhancement of remote sensing image based on Contourlet transform[J]. Optics and Precision Engineering. 2008, 16(10):2030-2037.
[24] Dong Liang. Image enhancement based on the nonsubsampled contourlet transform and adaptive threshold[J]. Acta Electronica Sinica. 2008, 36(3):527-530.
[25] JiangPing Zhou. Nonsubsampled contourlet transform: Construction and application in enhancement[C]. International Conference on Image Processing, ICIP. 2005, 1:469-472.
[26] YuHeng Sha, Fang Liu. SAR image enhancement based on nonsubsampled contourlet transform[J]. Journal of Electronics and Information Technology. 2009, 31(7):1716-1721.
[27] Toshiyuki, T. Naohiko. Biometric Authentication by Hand Vein Patterns[C]. SICE Annual Conference in Sapporo. 2004, 249-253.
[28] Sang-Kyun Im, Hyung-Man Park. An Biometric Identication System by Extracting Hand Vein Patterns[J]. Journal of the Korean Physical Society. 2001:268-272.
[29]章毓晋.图像工程(上册):图像理解与计算机视觉[M].北京:清华大学出版社.2000,62-71.
[30]陈新武,田金文.基于子带收敛因子阈值法的轮廓波消噪方法[J].光电工程.2008,35(6):63-67.
[31] David L. Donoho. De-noising by soft-thresholding[J]. IEEE Transactions on Information Theory. 1995, 41(3):613-627.
[32] Y. H. Peng. De-noising by modified soft-thresholding[C]. IEEE Asia-Pacific Conference on Circuits and Systems. 2000, 760-762.
[33] Li Su, GuoLiang Zhao. Translation-invariant wavelet de-noising method with improved thresholding[R]. International Symposium on Communications and Information Technologies. 2005:599-602.
[34] HaiLong Zhu, TianYou Guo. Signal de-noising by improving soft thresholding on the dyadic wavelet transform[J]. Acta Automatica Sinica. 2004, 30(2):199-206.
[35]孟晋丽,潘泉.基于相邻尺度积系数的半软阈值小波滤波[J].电子与信息学报.2007,29(7):1649-1652.
[36] DunCan D. Po, M. N. Do. Directional multiscale modeling of images using the contourlet transform. IEEE Transactions on Image Processing[J]. 2006, 15(6):1610-1620.
[37] DunCan D. Po, M. N. Do. Directional Multiscale Statistical Modeling of Images[J]. The International Society for Optical Engineering. 2003, 5207:69-79.
[38]侯正信,任亮.一种新的全相位Contourlet离散变换在图像去噪中的应用[J].中国图象图形学报.2008,13(5):870-875.
[39]任洪娥,王海峰.基于小波-Contourlet变换的Cycle spinning硬阈值图像去噪方法[J].光学技术.2008,34(6):854-857,861.
[40]程光权,成礼智.基于平稳Contourlet变换的自适应阈值去噪[J].计算机应用研究.2008,25(2):473-474,487.
[41]徐华楠,刘哲.Contourlet变换及其在图像去噪中的应用研究[J].计算机应用研究.2009,26(2):401-405.
[42]程光权,成礼智.基于冗余Contourlet变换的图像相关法去噪[J].中国图象图形学报.2008,13(9):1678-1682.
[43]杨露,苏秀琴.基于Contourlet变换和形态学的图像去噪方法[J].光电子.激光.2008,19(11):1558-1560.
[44]吴文怡,吴一全.基于Contourlet变换的红外弱小目标检测方法[J].红外与激光工程.2008,37(1):136-138.
[45]林喜荣,庄波,苏晓生等.人体手背血管图像的特征提取及匹配.清华大学学报(自然科学版).2003,43(2):164-167.
[46]程玉宝,徐海萍.基于小波重构和灰度分段的红外图像放大增强[J].红外技术.2008,30(10):567-570.
[47] ZiFei Yan, Miao Yu. Sublingual vein segmentation from near infrared sublingual images. Journal of Computer-Aided Design and Computer Graphics. 2008, 20(12):1569-1574.
[48] Herbert Zeman. Optimization of subcutaneous vein contrast enhancement[J]. TheInternational Society for Optical Engineering. 2000, 3911:50-57.
[49] TianHu Lei, Jayaram Udupa. Separation of artery and vein in contrast enhanced MRA images[R]. The International Society for Optical Engineering. 2000, 3978:233-244.
[50] Y. S. Jung, B. H. Nam. Vein recognition using infra-red imaging[C]. Proceedings of the SICE Annual Conference. 2005, 2904-2907.
[51]温学兵,赵江魏.基于小波去噪和直方图模板均衡化的手指静脉图像增强[J].吉林大学学报:理学版.2008,46(2):291-292.
[52]丁宇航.手背静脉识别技术研究[D].哈尔滨:哈尔滨工程大学,2006,11-84.
[53] X. Wen. A new algorithm for enhancing the contrast of finger-vein image[J]. Journal of Information and Computational Science. 2006, 3:929-934.
[54] JianGuo Wang, WeiYun Yau. Person recognition by fusing palmprint and palm vein images based on "Laplacianpalm" representation[J]. Computer Vision and Pattern Recognition. 2008: 1531-1544.
[55]李伟华,庄奕琪等.电子器件噪声高斯性和线性的定量分析方法[J].西安电子科技大学学报:自然科学版.2009,36(6):1059-1062.
[56] Shi Zhao, YiDing Wang. Biometric identification based on low-quality hand vein pattern images[C]. Proceedings of the 7th International Conference on Machine Learning and Cybernetics. 2008, 2:1172-1177.
[57] Dan Shi, QingWu Li. Infrared image nonlinear enhancement algorithm based on contourlet transform. Acta Optica Sinica. 2009, 29(2):342-346.