图像残差的手指静脉特征间接提取的研究  

Research on extracting human finger vein pattern characteristics based on residual image

作　　者：余成波[1] 周召敏[1] 李洪兵[1,2] 李彦林[1] 

机构地区：[1]重庆理工大学远程测试与控制技术研究所,重庆400050 [2]重庆三峡学院,重庆404000

出　　处：《计算机工程与应用》2010年第28期167-169,174,共4页Computer Engineering and Applications

基　　金：重庆市自然科学基金重点项目No.CSTC2007BA2023;重庆市教育委员会科学技术研究项目No.KJ070620~~

摘　　要：根据手指静脉对近红外的吸收特性,提出了一种基于背景图像的构造以得到第一次残差图像,通过调节比例系数得到第二次残差图像,以间接的方式获取静脉的特征。经过该算法和其他直接提取算法的对比,表明该文算法具有方法简单,易于实现,特别是获取的第二次残差图像对模糊和低质量部分的图片得到了比其他算法更加合理的特征信息,真实性强,同时也达到了准确、连续、光滑的要求。According to the absorption feature of the finger towards the near-infrared,this paper proposes an approach to obtain the first residual error image based on the construction of background image,get the second residual error image through adjusting the scale factors,and finally indirectly gain the features of the vein.This paper detailedly discusses the absorption feature of the vein towards the near-infrared and the comparison between the error-residual extraction algorithm and some other direct extraction algorithms.This method tends to be simpler and more realizable,especially in the process of obtaining the second residual error image,much more accurate feature information can be got,simultaneously conforming to the requirements of the accuracy,continuity and smoothness.

关 键 词：手指静脉 吸收特征 背景图像 残差图像 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]