基于稀疏结构噪声检测的指静脉图像去噪算法

doi:10.19678/j.issn.1000-3428.0057616

摘要/Abstract

摘要： 针对携带污染噪声的指静脉图像中背景区域、静脉区域和噪声区域的稀疏特性，提出一种改进的指静脉图像去噪算法。利用指静脉稀疏结构特性建立鲁棒主成分分析（RPCA）模型，通过交替方向乘子法求解RPCA模型获得含稀疏目标的前景图像并对其进行阈值分割以提取噪声分布图，同时根据提取结果建立修复优先度规则和自适应选择性滤波模板，实现指静脉图像的去噪处理。实验结果表明，与自适应非局部均值去噪算法和基于分数阶微分梯度噪声检测的去噪算法相比，在零误识情况下该算法处理后的带噪指静脉图像拒识率平均降低5.95%和3.64%，有效提升了带噪指静脉图像的识别性能。

关键词: 指静脉, 鲁棒主成分分析, 噪声检测, 噪声去除, 稀疏性

Abstract: Aiming at the sparse characteristics of the background area,vein area and noise area in the finger vein image with pollution noise,this paper proposes an improved denoising algorithm for finger vein images.Based on the sparse structure of finger veins,a Robust Principal Component Analysis(RPCA) model is established,and solved by using the Alternating Direction Method of Multipliers(ADMM) to get the foreground image with sparse targets.For the obtained image,threshold segmentation is implemented to extract the noise distribution image,and the repair priority rule and adaptive selective filter template based on the extraction result are established to remove noise.Experimental results show that in the case of zero FAR,the FRR of the finger vein images processed by this algorithm is reduced by 5.95% and 3.64% respectively compared with processed by the Adaptive Non-Local Means(ANLM) denoising algorithm,and processed by denoising algorithm based on fractional order Fractional Gradient(FG) noise detection.The proposed algorithm effectively improves the recognition performance of noisy finger vein images.

Key words: finger vein, Robust Principal Component Analysis(RPCA), noise detection, noise removal, sparsity

中图分类号:

TP391.41

何必锋, 沈雷, 何晶, 蒋寒琼. 基于稀疏结构噪声检测的指静脉图像去噪算法[J]. 计算机工程, 2021, 47(5): 236-243.

HE Bifeng, SHEN Lei, HE Jing, JIANG Hanqiong. Denoising Algorithm for Finger Vein Images Based on Sparse Structure Noise Detection[J]. Computer Engineering, 2021, 47(5): 236-243.

http://www.ecice06.com/CN/Y2021/V47/I5/236

参考文献

[1] LIU Zhi,SONG Shangling.An embedded real-time finger-vein recognition system for mobile devices[J].IEEE Transactions on Consumer Electronics,2012,58(2):522-527.
[2] XI Xiaoming.Research on the key problems of finger vein recognition[D].Jinan:Shangdong University,2015.(in Chinese)袭肖明.手指静脉识别若干关键问题研究[D].济南:山东大学,2015.
[3] CHEN Meimei.Research on denoise and segmentation algorithm of finger vein image[D].Changchun:Jilin University,2010.(in Chinese)陈玫玫.手指静脉图像的去噪与分割算法研究[D].长春:吉林大学,2010.
[4] LIU Tong.Key technologies research on finger vein recognition for low quality images[D].Changsha:National University of Defense Technology,2014.(in Chinese)刘通.面向低质量图像的手指静脉识别关键技术研究[D].长沙:国防科技大学,2014.
[5] HE Dongxia.The research and application of digital image de-noising algorithm[D].Yan'an:Yan'an University,2015.(in Chinese)贺东霞.数字图像去噪算法的研究与应用[D].延安:延安大学,2015.
[6] ZHANG Wenwen.Research on image denoising based in the transform domain[D].Hangzhou:Zhejiang University,2013.(in Chinese)张稳稳.基于变换域的图像去噪算法研究[D].杭州:浙江大学,2013.
[7] HAN Dianyuan.Study of algorithms improvement for simple neighborhood averaging in image denoising[J].Journal of Weifang University,2006,6(6):12-14.(in Chinese)韩殿元.简单邻域平均图像去噪算法的改进研究[J].潍坊学院学报,2006,6(6):12-14.
[8] SRAVANI B,RAO M V N.Removing of high density salt and pepper noise using fuzzy median filter[C]//Proceedings of 2014 International Conference on High Performance Computing and Applications.Washington D.C.,USA:IEEE Press,2014:1-6.
[9] YANG Zhuodong,ZHANG Xin,ZHANG Tao,et al.Image denoising based on improved adaptive median filter[J].Communications Technology,2015,48(11):1257-1260.(in Chinese)杨卓东,张欣,张涛,等.改进自适应中值滤波的图像去噪[J].通信技术,2015,48(11):1257-1260.
[10] ZHANG Ning,SONG Xiaopeng,LIU Yi,et al.An adaptive nonlocal mean denoising algorithm based on intuitionistic fuzzy divergence[J].Journal of Test and Measurement Technology,2020,34(1):1-8.(in Chinese)张宁,宋小鹏,刘祎,等.基于直觉模糊散度的自适应非局部均值去噪算法[J].测试技术学报,2020,34(1):1-8.
[11] LU C T,CHEN Y Y,WANG L L,et al.Removal of salt-and-pepper noise in corrupted image using three-values-weighted approach with variable-size window[J].Pattern Recognition Letters,2016,80:188-199.
[12] VARATHARAJAN R,VASANTH K.An adaptive decision based kriging interpolation algorithm for the removal of high density salt and pepper noise in images[J].Computers & Electrical Engineering,2017,70:447-461.
[13] WANG Gang,MOU Jianping,YANG Zhuzhong.Noise detection algorithm based on fractional differential gradient[J].Journal of Sichuan University(Natural Science Edition),2014,51(3):483-488.(in Chinese)王刚,牟剑平,杨柱中.基于分数阶微分梯度的噪声检测算法[J].四川大学学报(自然科学版),2014,51(3):483-488.
[14] ZHOU Yang.Research on robust principle component analysis and its applications[D].Guangzhou:Guangdong University of Technology,2017.(in Chinese)周杨.鲁棒主成分分析的算法研究及其应用[D].广州:广东工业大学,2017.
[15] CANDES E J,LI X D,MA Y,et al.Robust principal component analysis?[J].Journal of the Association for Computing Machinery,2011,58(3):1-37.
[16] GAO Z,CHEONG L F,SHAN M.Block-sparse RPCA for consistent foreground detection[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2012:690-703.
[17] EBADI S E,IZQUIERDO E.Foreground segmentation with tree-structured sparse RPCA[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2018,40(9):2273-2280.
[18] LI Ji,ZHAO Lina,HOU Xuke.Matrix recovery by randomly permuted Alternating Direction Method of Multipliers(ADMM)[J].Journal of Beijing University of Chemical Technology(Natural Science Edition),2017,44(3):123-128.(in Chinese)李吉,赵丽娜,侯旭珂.通过随机排序的交替方向乘子法的矩阵恢复[J].北京化工大学学报(自然科学版),2017,44(3):123-128.
[19] XU Yangyang,YIN Wotao,WEN Zaiwen,et al.An alternating direction algorithm for matrix completion with nonnegative factors[J].Frontiers of Mathematics in China,2012,7(2):365-384.
[20] CHEN C,NG M K,ZHAO X L.Alternating direction method of multipliers for nonlinear image restoration problems[J].IEEE Transactions on Image Processing,2015,24(1):33-43.
[21] ZHOU Y B,KUMAR A.Human identification using palm-vein images[J].IEEE Transactions on Information Forensics and Security,2011,6(4):1259-1274.

选择文件类型/文献管理软件名称

选择包含的内容