基于皮肤散射模型的手指静脉图像去模糊化

崔建江; 李琦; 薛定宇; 李思远

doi:10.3788/OPE.20162413.0727

您当前的位置：

首页 >

文章列表页 >

基于皮肤散射模型的手指静脉图像去模糊化

更新时间：2020-08-13

- 基于皮肤散射模型的手指静脉图像去模糊化
- Finger vein image deblurring method based on skin scattering models
- 光学精密工程 2016年24卷第10s期页码：727-732
- 作者机构：
  
  1. 东北大学信息工程与科学学院,辽宁沈阳,110819
  2. 辽宁科技大学电子信息与工程学院,辽宁鞍山,114051
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目（No.61174145）()
- DOI：10.3788/OPE.20162413.0727
  中图分类号： TP391.41
- 收稿日期：2016-05-19，
  
  修回日期：2016-06-07，
  
  纸质出版日期：2016-11-14
- 稿件说明：
移动端阅览
崔建江, 李琦, 薛定宇等. 基于皮肤散射模型的手指静脉图像去模糊化[J]. 光学精密工程, 2016,24(10s): 727-732

CUI Jian-jiang, LI Qi, XUE Ding-yu etc. Finger vein image deblurring method based on skin scattering models[J]. Editorial Office of Optics and Precision Engineering, 2016,24(10s): 727-732
崔建江, 李琦, 薛定宇等. 基于皮肤散射模型的手指静脉图像去模糊化[J]. 光学精密工程, 2016,24(10s): 727-732 DOI： 10.3788/OPE.20162413.0727.

CUI Jian-jiang, LI Qi, XUE Ding-yu etc. Finger vein image deblurring method based on skin scattering models[J]. Editorial Office of Optics and Precision Engineering, 2016,24(10s): 727-732 DOI： 10.3788/OPE.20162413.0727.

摘要

针对手指静脉图像在采集时出现的模糊现象，提出了一种基于去除皮肤散射的手指静脉图像复原算法。根据皮肤光学的实验分析，确定了手指静脉图像采集过程中皮肤对近红外光的散射模型，并自适应地进行手指静脉图像的点扩散函数的估计；再根据得到的点扩散函数采用维纳滤波完成手指静脉图像的复原。采用该算法对3幅手指静脉图像进行了复原，并对复原结果进行了定量分析，结果显示本文算法可将图像的边缘平均梯度提高3.903。最后，将本文算法与3种常用的手指图像增强算法进行了对比。结果表明，相比于直方图均衡化方法、限制对比度自适应直方图均衡化方法（CLAHE）和高频强调滤波方法，本文算法复原得到的静脉的宽度及结构与原图像最为接近，阴影少，静脉失真情况最小，峰值信噪比最高。

Abstract

Aiming at the image blur in the near-infrared finger vein recognition

an algorithm for restoration of the finger vein image based on elimination of the skin scattering was put forward. A scattering model against near-infrared light during the collection of finger vein image was established through experimental analysis on the skin optics. Based on the model

the point spread function of the finger vein image was adaptively estimated and then employed to restore the finger vein image by using Wiener filter. Three vein images were restored quantitatively by the proposed algorithm. The result shows that the average gradients of edge of the three images increase to 7.636

6.877 and 6.750 respectively. Compared with POSHE algorithm

CLAHE algorithm and high-frequency emphasize filter algorithm

the width and structure of the restored vein image is more consistent with those of the original image with the minimum shadow and distortion and the highest signal to noise ratio.

关键词

Keywords

references

崔建江,贾旭,刘晶,等.基于计盒维数和多小波的静脉图像特征提取[J]. 东北大学学报(自然科学版),2010,31(10):1397-1400. CUI J J,JIA X,LIU J,et al.. Vein image feature extraction based on box counting dimension and multiple wavelets[J]. Journal of Northeastern University(Natural Science),2010,31(10):1397-1400. (in Chinese)

YANG J F, YANG J L. Multi-channel Gabor filter design for finger-vein image enhancement[C].Proceedings of the 5th International Conference on Image and Graphics,Xian,P.R. China:ICIG, 2009:87-91.

ZHANG J, YANG J F. Finger-vein image enhancement based on combination of gray-level grouping and circular Gabor filter[C].Proceedings of the International Conference on Information Engineering and Computer Science,Wuhan,P.R. China:ICIECS,2009:1-4.

YANG J F, YAN M F. An improved method for finger-vein image enhancement[C].Proceedings of the 2010 IEEE 10th International Conference on Signal Processing,Beijing,P.R. China:ICSP,2010:1706-1709.

YANG J F, YANG J L, SHI Y H. Combination of Gabor wavelets and circular Gabor filter for finger-vein extraction[C].Proceedings of the 5th International Conference on Intelligent Computing,Ulsan,South Korea:ICIC,2009:346-354.

LEE E C, KANG R P.Image restoration of skin scattering and optical blurring for finger vein recognition[J].Optics and Lasers in Engineering,2011,49(7):816-828.

WANG J, TAN Y. A novel genetic programming algorithm for designing morphological image analysis method[C].Proceedings of the 2nd International Conference on Advances in Swarm Intelligence,Chongqing,P.R.China:ICSI,2011:549-558.

WANG J, TAN Y. Morphological image enhancement procedure design by using genetic programming[C].Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation,Dublin,Ireland:GECCO,2011:1435-1442.

ZHANF Z B, MA S L, HAN X. Multiscale feature extraction of finger-vein patterns based on curvelets and local interconnection structure neural network[C].Proceedings of the 18th International Conference on Pattern Recognition,Hong Kong, P.R.China:ICPR 2006:145-148.

OLSEN M A, HARTUNGD, BUSCHC. Contrast enhancement and metrics for biometric vein pattern recognition[C].Proceedings of the 6th International Conference on Intelligent Computing,Changsha,P.R.China:ICIC 2010:425-434.

秦斌. 手静脉身份识别技术[J]. 现代电子技术,2011,34(4):169-177. QIN B. Hand Vein Identification Technique[J]. Modern Electronics Technique,2011,34(4):169-177. (in Chinese)

陈荣, 黄宝华, 王月云. 皮肤的光学模型[J]. 激光生物学报,2005,14(6):401-404. CHEN R,HUANG B H,WANG Y Y. The optical model of human skin[J].Acta Laser Biology Sinica,2005,14(6):401-404. (in Chinese)

李晖, 谢树森, 陆祖康. 生物组织的可见光与近红外光散射模型[J]. 光学学报,1999,19(12):1661-1666. LI H,XIE S S,LU Z K. A New Model of the Light Scattering in Biological Tissue for Visible and Near Infrared Region[J].Acta Optica Sinica,1999,19(12):1661-1666. (in Chinese)

GEMERT M J C V, JACQUES S L, STERENBORG H J C M.. Skin Optics[J].IEEE Transactions on biomedical engineering,1989,36(12):1146-1154.

SHIMIZU K, TOCHIO K, KATO Y. Improvement of transcutaneous fluorescent images with a depth-dependent point-spread function[J].Appl. Opt,2005,44(11):2154-2161.

龚玮, 谢树森. 皮肤的光学模型和光学性质[J]. 中国激光医学杂志,2010,2(19):114-118. GONG W,XIE S S.Optical Model and Optical Properties of Human Skin[J].Chinese Journal of Laser Medicine & Surgery,2010,2(19):114-118. (in Chinese)

张冬梅. 低质量手指静脉图像增强[D].重庆:重庆理工大学,2010. ZHANG D M.Low Quality Finger Vein Image Enhancement[D].Chongqing:chongqing university of technology,2010. (in Chinese)

高晓燕, 马军山, 吴佳杰. 手指静脉图像增强算法研究[J]. 光学仪器,2010,32(4):29-32. GAO X Y, MA J S, WU J J. The research of finger-vein image enhancement algorithm[J].Optical Instruments,2010,32(4):29-32. (in Chinese)

浏览量

199

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于导向滤波Retinex和自适应Canny的图像边缘检测

自适应色彩补偿和多尺度融合的水下图像增强

基于双目结构光周视扫描的3D件三维重构与位姿估计研究

重叠分数与匹配矩阵驱动的部分重叠点云配准网络设计

基于频域-空域混合注意力的降质遥感图像质量增强