摘要: 在虹膜图像的采集过程中,由于现阶段硬件设备和虹膜本身特性的限制,不可避免地会采集到模糊的图像。模糊的虹膜图像由于其纹理细节信息的丢失,造成了虹膜识别系统性能的下降。提出了一种适用于虹膜图像的恢复算法,以增强模糊图像的质量,提升系统的识别准确率。此去模糊算法充分利用虹膜图像的独特性质作为先验知识,使用了一种由粗到精的结构,模糊核首先在参数模型的刻画下进行初始化,然后转而使用像素级的模型进行优化更新,以准确表达真实的模糊原因。在优化过程中,使用了一种基于非局部性的正则化手段,并通过对虹膜图像的分析仅选取了可靠的区域来对清晰图像进行估计,以同时保证算法的可靠性和高效性。在实验中通过与现有算法的比较,可以发现本算法对于运动模糊和离焦模糊的虹膜图像均能够获得更大程度的识别性能提升,验证了本算法的有效性。
[1] Jain A,Bolle R,Pankanti S.Biometrics:Personal identification in networked society[M].Kluwer Academic Publishers,1999 [2] Daugman J.High confidence visual recognition of persons by a test of statistical independence[J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1993,15(11):1148-1161 [3] Li Xing-guang,Sun Zhe-nan,Tan Tie-niu.Comprehensive as-sessment of iris image quality[C]∥IEEE Int’l Conf.on Image Processing.ICIP2011.Brussels,Belgium ,September 2011:3117-3120 [4] Fergus R,Singh B,Hertzmann A,et al.Removing camera shake from a single photograph[J].ACM Trans.on Graphics,2006(25):787-794 [5] Kang B,Park K.Real-time image restoration for iris recognition systems[J].IEEE Trans.on Systems,Man,and Cybernetics,Part B:Cybernetics,2007(37):1555-1566 [6] Huang Xin-yu,Ren Liu,Yang Rui-gang.Image deblurring forless intrusive iris capture[C]∥IEEE Conf.on Computer Vision and Pattern Recognition.IEEE,2009:1558-1565 [7] Kang B,Park K.Restoration of motion-blurred iris images onmobile iris recognition devices.Optical Engineering,2008(47):117-202 [8] Cho S,Lee S.Fast motion deblurring[J].ACM Trans.on Graphics,2009(28) [9] Shan Q,Jia J,Agarwala A.High-quality motion deblurring from a single image[C]∥ACM Trans.on Graphics,2008,27:73 [10] Olshausen B,Field D.Emergence of simple-cell receptive fieldproperties by learning a sparse code for natural images[J].Nature,1996,381:607-609 [11] Buades A,Coll B,Morel J-M.A non-local algorithm for imagedenoising[C]∥IEEE Conf.on Computer Vision and Pattern Recognition.IEEE,2005,2:60-65 [12] Levin A,Weiss Y,Durand F,et al.Understanding and evalua-ting blind deconvolution algorithms[C]∥IEEE Conf.on Computer Vision and Pattern Recognition IEEE.2009:1964-1971 [13] Xu Li,Jia Jia-ya.Two-phase kernel estimation for robust motion deblurring[C]∥European Conference on Computer Vision.2010:157-170 [14] Wei Zhuo-shi,Tan Tie-niu,Sun Zhe-nan,et al.Robust and fast assessment of iris image quality[C]∥Advances in Biometrics.2005:464-471 [15] He Zhan-feng,Tan Tie-niu,Sun Zhe-nan,et al.Toward accurate and fast iris segmentation for iris biometrics[J].IEEE Trans.on Pattern Analysis and Machine Intelligence, 2009,31(9):1670-1684 [16] Daugman J.How iris recognition works[J].IEEE Trans.on Cir-cuits and Systems for Video Technology,2004,14(1):21-30 [17] Guestrin E,Eizenman M.General theory of remote gaze estimation using the pupil center and corneal reflections[J].IEEE Trans.on Biomedical Engineering,2006,53(6):1124-1133 [18] Krishnan D,Tay T,Fergus R.Blind deconvolution using a normalized sparsity measure[C]∥IEEE Conf.on Computer Vision and Pattern Recognition.IEEE,2011:233-240 [19] ICE.www.nist.gov/itl/iad/ig/ice.cfm |
No related articles found! |
|