级联型多测度可见光虹膜图像质量评价方法
|
摘要
移动终端虹膜识别是虹膜识别的一个新的发展方向。应用背景的改变令移动终端采集所得的虹膜图像可能受到光照、遮挡、位置错误、失焦或手持设备不稳定等因素造成的模糊及其他多种类型的干扰,严重影响识别准确率和系统运行效率,为此需要评价虹膜图像质量。提出一种应用于可见光虹膜图像的质量评价方法,此方法包含分三个层次的判别级联模型,逐级评价相应的感兴趣区域及图像的质量。实验结果证明,该模型能够在实现虹膜区域检测的同时排除存在严重干扰的虹膜图像,并对虹膜区域的反射光干扰和模糊程度给出定量评价,提高了虹膜识别的正确率与运算效率。
The Iris recognition of mobile terminal is a new development direction of iris recognition.The change of the application background makes the iris image acquired by the mobile terminal likely to Suffer from blur and other kinds of interference caused by illumination, occlusion, position error, defocus or unstable devices handholding, which seriously affects the recognition accuracy and system operation efficiency. Therefore, it is necessary to evaluate the iris image quality, and a quality evaluation method applied to visible iris image is proposed, which includes three levels of discriminant cascaded models to evaluate the corresponding regions of interest and image quality according to the levels. The experimental results show that the model can eliminate the iris image with serious interference while detecting the iris region, and give a quantitative evaluation of the reflected light interference and blur in the iris region,thus improving the accuracy and efficiency of iris recognition..
The Iris recognition of mobile terminal is a new development direction of iris recognition.The change of the application background makes the iris image acquired by the mobile terminal likely to Suffer from blur and other kinds of interference caused by illumination, occlusion, position error, defocus or unstable devices handholding, which seriously affects the recognition accuracy and system operation efficiency. Therefore, it is necessary to evaluate the iris image quality, and a quality evaluation method applied to visible iris image is proposed, which includes three levels of discriminant cascaded models to evaluate the corresponding regions of interest and image quality according to the levels. The experimental results show that the model can eliminate the iris image with serious interference while detecting the iris region, and give a quantitative evaluation of the reflected light interference and blur in the iris region,thus improving the accuracy and efficiency of iris recognition..
引文
[1]李海青,孙哲南,谭铁牛,等.虹膜识别技术进展与趋势[J].信息安全研究,2016,2(1):40-43.LI Haiqing,SUN Zhenan,TAN Tieniu,et al.Progress and trends in iris recognition[J].Journal of Information Securyity Research,2016,2(1):40-43.
[2]BARRA S,CASANOVA A,NARDUCCI F,et al.Ubiquitous iris recognition by means of mobile devices[J].Pattern Recognition Letters,2015,57:66-73.
[3]李星光,孙哲南,谭铁牛.虹膜图像质量评价综述[J].中国图象图形学报,2014,19(6):813-824.LI Xingguang,SUN Zhenan,TAN Tieniu,et al.Overview of iris image quality-assessment[J].Journal of Image and Graphics,2014,19(6):813-824.
[4]罗晓庆,周响金.基于灰度特征的虹膜图像质量评价方法[J].微计算机信息,2012(10):258-260.LUO Xiaoqing,ZHOU Xiangjin.A quality evaluation method of iris images based on gradation feature[J].Microcomputer Information,2012(10):258-260.
[5]蔺勇,杨雅宁.虹膜图像质量评价方法研究[J].宁夏师范学院学报,2014,35(6):71-78.LIN Yong,YANG Yaning.Study on the assessment method of iris image quality[J].Journal of Ningxia Normal University,2014,35(6):71-78.
[6]史春蕾,周凤文,胡雨露,等.虹膜图像的质量评价研究[J].液晶与显示,2016,31(12):1131-1136.SHI Chunlei,ZHOU Fengwen,HU Yulu,et al.Study for iris image quality assessment[J].Chinese Journal of Liquid Crystals and Displays,2016,31(12):1131-1136.
[7]LEE J C,SU Y,TU T M,et al.A novel approach to image quality assessment in iris recognition systems[J].Journal of Photographic Science,2010,58(3):136-145.
[8]王洪.无参考的虹膜图像质量评估算法的研究[D].沈阳:东北大学,2014.WANG Hong.Research on no-reference iris image quality evaluation algorithm[D].Shenyang:Northeastern University,2014.
[9]Center for Biometrics and Security Research.Chinese Academy of Science Institute of Automation.DatabaseCASIA-IrisV4[DB/OL].[2018-03-21].http://www.cbsr.ia.ac.cn/china/Iris Databases CH.asp.
[10]MARSICO M D,NAPPI M,RICCIO D,et al.Mobile iris challenge evaluation(MICHE)-I,biometric iris dataset and protocols[J].Pattern Recognition Letters,2015,57:17-23.
[11]VIOLA P,JONES M J.Robust real-time face detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[12]VIOLA P,JONES M J.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001IEEE Computer Society Conference on Computer Vision and Pattern Recognition,December 8-14,2001,Kauai,Hawaii.IEEE Computer Society,2001:I-511-I-518.
[13]OSTU N.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems Man and Cybernetics,1979,SMC-9(1):62-66.
[14]VISHWANATH M,OWENS R M,IRWIN M J.VLSIarchitectures for the discrete wavelet transform[J].IEEETransactions on Circuits and Systems II:Analog and Digital Signal Processing,1995,42(5):305-316.
[15]薛万勋,卞春江,陈红珍.基于点锐度和平方梯度的图像清晰度评价方法[J].电子设计工程,2017(8):163-167.XUE Wanxun,BIAN Chunjiang,CHEN Hongzhen.Image clarity evaluation based on point sharpness and square gradient[J].Electronic Design Engineering,2017(8):163-167.
[16]孙红利,冯旗,董峰.图像清晰度评价算法研究[J].传感器与微系统,2017,36(2):67-70.SUN Hongli,FENG Qi,DONG Feng.Research on algorithm for image clarity evaluation[J].Transducer and Microsystem Technologies,2017,36(2):67-70.
[2]BARRA S,CASANOVA A,NARDUCCI F,et al.Ubiquitous iris recognition by means of mobile devices[J].Pattern Recognition Letters,2015,57:66-73.
[3]李星光,孙哲南,谭铁牛.虹膜图像质量评价综述[J].中国图象图形学报,2014,19(6):813-824.LI Xingguang,SUN Zhenan,TAN Tieniu,et al.Overview of iris image quality-assessment[J].Journal of Image and Graphics,2014,19(6):813-824.
[4]罗晓庆,周响金.基于灰度特征的虹膜图像质量评价方法[J].微计算机信息,2012(10):258-260.LUO Xiaoqing,ZHOU Xiangjin.A quality evaluation method of iris images based on gradation feature[J].Microcomputer Information,2012(10):258-260.
[5]蔺勇,杨雅宁.虹膜图像质量评价方法研究[J].宁夏师范学院学报,2014,35(6):71-78.LIN Yong,YANG Yaning.Study on the assessment method of iris image quality[J].Journal of Ningxia Normal University,2014,35(6):71-78.
[6]史春蕾,周凤文,胡雨露,等.虹膜图像的质量评价研究[J].液晶与显示,2016,31(12):1131-1136.SHI Chunlei,ZHOU Fengwen,HU Yulu,et al.Study for iris image quality assessment[J].Chinese Journal of Liquid Crystals and Displays,2016,31(12):1131-1136.
[7]LEE J C,SU Y,TU T M,et al.A novel approach to image quality assessment in iris recognition systems[J].Journal of Photographic Science,2010,58(3):136-145.
[8]王洪.无参考的虹膜图像质量评估算法的研究[D].沈阳:东北大学,2014.WANG Hong.Research on no-reference iris image quality evaluation algorithm[D].Shenyang:Northeastern University,2014.
[9]Center for Biometrics and Security Research.Chinese Academy of Science Institute of Automation.DatabaseCASIA-IrisV4[DB/OL].[2018-03-21].http://www.cbsr.ia.ac.cn/china/Iris Databases CH.asp.
[10]MARSICO M D,NAPPI M,RICCIO D,et al.Mobile iris challenge evaluation(MICHE)-I,biometric iris dataset and protocols[J].Pattern Recognition Letters,2015,57:17-23.
[11]VIOLA P,JONES M J.Robust real-time face detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[12]VIOLA P,JONES M J.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001IEEE Computer Society Conference on Computer Vision and Pattern Recognition,December 8-14,2001,Kauai,Hawaii.IEEE Computer Society,2001:I-511-I-518.
[13]OSTU N.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems Man and Cybernetics,1979,SMC-9(1):62-66.
[14]VISHWANATH M,OWENS R M,IRWIN M J.VLSIarchitectures for the discrete wavelet transform[J].IEEETransactions on Circuits and Systems II:Analog and Digital Signal Processing,1995,42(5):305-316.
[15]薛万勋,卞春江,陈红珍.基于点锐度和平方梯度的图像清晰度评价方法[J].电子设计工程,2017(8):163-167.XUE Wanxun,BIAN Chunjiang,CHEN Hongzhen.Image clarity evaluation based on point sharpness and square gradient[J].Electronic Design Engineering,2017(8):163-167.
[16]孙红利,冯旗,董峰.图像清晰度评价算法研究[J].传感器与微系统,2017,36(2):67-70.SUN Hongli,FENG Qi,DONG Feng.Research on algorithm for image clarity evaluation[J].Transducer and Microsystem Technologies,2017,36(2):67-70.