对虹膜识别系统来说，所采集虹膜图像的质量好坏直接影响识别是否成功。本文针对散焦模糊和眼睑睫毛遮挡问题提出了一种新的虹膜图像质量评价方法：判断图像是否散焦模糊采用了 LoG 算子提取瞳孔两侧局部虹膜的高频能量，判断虹膜是否有眼睑严重遮挡采用了计算瞳孔上方指定矩形区域的灰度均值，同时计算该区域的水平梯度来衡量虹膜受睫毛遮挡的程度。仿真实验表明，算法的平均处理速度0．0209 s/帧，满足实时虹膜识别系统的需求，是一种快速有效的虹膜图像质量评价算法。
The quality of collecting iris image is vital to whether recognizing iris image is right in iris recognition system.A new algorithm is proposed for the defocused and occluded iris images.Firstly the high frequency power of the right and left part of the pupil is calculated by Laplacian of Gaussian operator to discard the defocused images.Secondly,the average gray value of the upper region of the pupil is computed to discard the occluded images by eyelid.Finally,the occluded degree by eyelash is measured through the gradient information of the upper region of the pupil.The experimental results show that,the average processing speed of the algorithm is 0.020 9 s per frame,which fully meets the requirement of real-time iris recognition system,and also shows this algorithm is fast and efficient for iris image quality evaluation.
参考文献
| [1] | 盖健;刘小华;李锐杰;宁尚军.基于LBP的图像集人脸识别算法[J].东北师大学报（自然科学版）,2015(4):84-87. |
| [2] | 康梦博;秦贵和.车载MOST摄像头和人脸识别接口的设计与实现[J].东北师大学报（自然科学版）,2015(4):74-78. |
| [3] | 陈文静;金华.基于人脸与虹膜的多生物特征融合识别算法研究[J].中国人民公安大学学报（自然科学版）,2015(1):77-79. |
| [4] | Daugman J..How iris recognition works[J].IEEE Transactions on Circuits and Systems for Video Technology,20041(1):21-30. |
| [5] | John Daugman.Statistical richness of visual phase information: update on recognizing persons by iris patterns[J].International Journal of Computer Vision,20011(1):25-38. |
| [6] | Estimating and Fusing Quality Factors for Iris Biometric Images[J].IEEE transactions on systems, man, and cybernetics, Part A. Systems and humans: A publication of the IEEE Systems, Man, and Cybernetics Society,20103(3):509. |
| [7] | 李星光;孙哲南;谭铁牛.由粗到精的虹膜图像离焦模糊评价方法[J].计算机科学与探索,2014(1):81-89. |
| [8] | 张强;郭宝龙.基于非采样Contourlet变换多传感器图像融合算法[J].自动化学报,2008(2):135-141. |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%