Image restoration of skin scattering and optical blurring for finger vein recognition

Finger vein recognition has been adopted due to its high recognition rate and the invisibility of vein in visible light. However, because a finger vein pattern is not distinctive due to light scattering in the skin layer, the localization of a finger vein pattern region using an image processing algorithm is a difficult procedure. Also, optical blurring increases these difficulties. We propose a new finger vein image restoration method to deal with skin scattering and optical blurring. Our research is novel in three ways compared to previous studies. Firstly, the amount of optical blurring of a finger vein image is measured based on the average gradient of the orthogonal profile of a finger edge. Secondly, the accurate point spread function (PSF) of optical blurring is adaptively determined based on the orthogonal profile of a finger edge. Thirdly, using a constrained least square (CLS) filter and optimized parameters in terms of the lowest error of finger vein recognition, the restoration of a skin scattered and optically blurred finger vein pattern was performed. Experimental results show that the equal error rate (EER) of finger vein recognition with restoration was reduced by as much as 3.14% (5.05-1.91%) compared to the EER without restoration.     

Hand vein recognition based on the connection lines of reference point and feature point

According to the essential characters of the image topology, a new hand vein recognition algorithm based on the connection lines of reference point and feature points is proposed. In this method, the intersection points and the endpoints of the vein image are used as feature points. After the intersection points and the endpoints selected as feature points, the reference point for image matching are extracted from these points. The relative distances between the reference point and the feature points and the angles between the adjacent connections of the reference point and feature points are calculated and used as recognition features. Finally these two features are combined for hand vein recognition. This method can effectively overcome the influence on the recognition results caused by image translation and rotation. Experimental results show that the proposed algorithm is able to achieve hand vein recognition reliably and quickly.     

基于手指静脉特征图像的加密研究

移动互联下的信息安全是目前研究的热门,本文从手指静脉图像的加密出发,首先对手指静脉图像的特征进行了提取,通过构建图像平滑器来获得静脉图像的大小,明暗区域的选择和特征图像的加强来获得采集后的静脉特征图像,其次对静脉图像采用基于小波基函数,Arnold映射,二次Logistic 映射和Baker变换的混合加密方式对进行加密。在相关系分析和差分攻击分析等方面实验比较,说明本文的算法具有很好的安全性和低耗时性,能够完全适应在移动互联环境中推广。     

Recognition of multibreak patterns by 8-neighborhood-based General Hough Transform

In this paper, an 8-neighborhood-based Generalized Hough Transform (ENGHT) for the recognition of multibreak patterns is proposed, which is different from the Generalized Hough Transform (GHT). The difference between ENGHT and GHT appears in the process for Reference-table (R-table) configuration and for pattern recognition. The theoretic and experimental results show that ENGHT can be employed in the recognition of multibreak patterns with a high precision and a high recognition speed, and reduce the difficulty during the recognition that arose from the broken patterns to be processed by the conventional GHT. ENGHT can be employed in pattern recognition, especially in the multibreak pattern recognition.     

Impact of NIR wavelength lighting in image acquisition on finger vein biometric system effectiveness

Finger vein biometric systems become increasingly more popular because they offer higher security comparing to other authentication solutions with respect to positive persons experience. Those systems operate on near infrared light (NIR) in wavelength range from around 700 to 1000 nm, however dedicated research to determine impact of NIR lighting on biometric system effectiveness has not been conducted and presented in the literature ever before. In this paper the study of correlation between wavelengths in NIR spectra and effectiveness of person identification in a biometric system is presented. To achieve that goal, a new model of image acquisition system allowing change of light wavelengths has been created and NIR finger vein dataset containing 11 556 images was established. Furthermore, this model was used to perform experimental work and proof that some NIR wavelengths better suit for vein patterns acquisition, allowing to increase the recognition effectiveness of finger vein biometric systems.     

基于LBP和多层次结构的异质手背静脉身份识别

针对多源异质的手背静脉异质图像的识别研究,提出了基于LBP和多层次结构的识别算法;首先对图像做适当的预处理,然后将LBP特征提取算法编码的手背静脉纹理特征图像作为多层次结构的输入,通过多层次结构的逐层由具体到抽象的特征提取,得到的特征具有更大的鲁棒性;最后该算法在多源异质的手背静脉图像库得到的识别率比传统的算法识别率高,达到96.57%;进一步表明该算法能够较好地解决由于多源异质问题对手背静脉识别所造成的识别率低的影响。     

多谱段短波红外小鼠静脉荧光观测成像研究

短波红外(short-wave infrared,SWIR)一般指900～1700 nm的光波段,是肉眼不可见的光波段,这种波段目前主流的探测器以InGaAs为主,主要用于军事、生物以及材料光谱分析等领域.短波红外荧光成像以其对生物组织光学损伤小、成像深度大、成像信噪比高、空间和时间成像分辨率高等特点,使得基于InGa...     

基于消失点检测算法的束靶红外图像畸变校正

传统的霍夫变换、Cannylines直线检测算法、霍夫概率变换方法在图像上的直线检测效果不佳,存在检测线段不连续不正确的问题,因而,利用Sobel滤波对红外图像横轴和纵轴两个方向分别进行锐化,通过线段检测(LSD)算法实现线段特征检测,进而经线段聚类拟合获得图像中完整的直线,通过对直线交点计算获得消失点,最后依据透视关系计算得到校正图像。实验结果表明,该方法可以实现对中性束红外图像的自动有效校正。     

基于Gabor小波变换的ICA火灾图像纹理识别算法

针对火灾图像纹理识别问题,提出了基于Gabor小波变换的ICA火灾图像纹理识别算法,并根据火灾图像纹理识别特点进行了优化。首先用不同尺度和方向的Gabor滤波器对待识别图像滤波,得到其特征图像,然后将特征图像转化成特征向量作为ICA的输入,得到基矢量子空间,再将测试图像经过Gabor滤波器的特征向量投影到ICA子空间中得到系数向量作为目标识别特征,最后用支持向量机进行识别。通过与Gabor滤波器法和ICA方法的对比实验,表明该算法可以在火灾纹理图像的识别率上比传统方法提高5%以上,为火灾图像识别提供了一种新思路。     

一种可识别破碎图形的特殊广义Hough变换方法

提出了一种与现有广义Hough变换(GHT)不同的识别破碎图形的方法.称为特殊广义Hough变换(SGHT)方法.该方法在参数表制作阶段和识别阶段，都与现有GHT方法不同.理论分析和实验的结果表明，采用SGHT方法， 可以解决常规GHT方法难以识别破碎图形的困难，且有很高的配准精度和速度，既可用于破碎图形的识别也可用于非破碎图形的识别，具有普适、快速和准确的特点. 关键词： 特殊广义Hough变换 广义Hough变换 参数表 8邻域     

一种基于分水岭的连接米粒自动分割算法

在连接米粒的分割中,分水岭分割算法对一个米粒经距离变换后常存在多个局部极小值而产生过分割.为解决该问题,应用形态学膨胀将检测的邻近的局部极小值合并成一个区域,使每个米粒内部只有一个局部极小值,再用分水岭算法进行分割.实验结果表明,对长江米、圆江米和粳米3个品种籽粒,提出的算法分割正确率分别达到87%、93%和92%,获得了满意的分割效果.     

手背静脉图像预处理算法研究

静脉识别是一种新兴的生物特征识别技术。介绍了静脉图像的采集原理,根据静脉血管的特点,重点对静脉图像预处理进行了研究。静脉图像预处理可分为静脉图像的标准化和静脉图像的二值化两个部分。针对二值化问题,提出了彩动态阈值法对静脉图像进行处理和增强,得到了较好的结果。     

基于特征匹配的快速鲁棒数字稳像

针对手持移动摄像装置拍摄视频序列相邻帧间存在平移、小角度旋转运动,而且易受噪声、光照变化的影响等问题,提出一种基于优化Oriented FAST and rotated BRIEF(ORB)特征匹配的实时鲁棒电子稳像算法。对相邻帧预处理后用Oriented FAST算子检测特征点,再用Rotated BRIEF描述提取的特征点并采用近邻汉明距离匹配特征点对,然后采用级联滤波去除误匹配点对,最后使用迭代最小二乘法(ILSM)拟合模型参量进行运动补偿实现稳像。图像匹配测试和稳像实验结果表明:基于改进的ORB算法的电子稳像方法补偿每一帧的时间均小于0.1 s,定位精度可达亚像素级,能有效补偿帧间平移旋转运动,而且对噪声和光照变化有较强鲁棒性。经稳像处理后,实拍视频质量明显提高,峰值信噪比（PSNR）平均提高了10 db。     

Finger crease pattern recognition using Legendre moments and principal component analysis

The finger joint lines defined as finger creases and its distribution can identify a person. In this paper,we propose a new finger crease pattern recognition method based on Legendre moments and principal component analysis (PCA). After obtaining the region of interest (ROI) for each finger image in the preprocessing stage, Legendre moments under Radon transform are applied to construct a moment feature matrix from the ROI, which greatly decreases the dimensionality of ROI and can represent principal components of the finger creases quite well. Then, an approach to finger crease pattern recognition is designed based on Karhunen-Loeve (K-L) transform. The method applies PCA to a moment feature matrix rather than the original image matrix to achieve the feature vector. The proposed method has been tested on a database of 824 images from 103 individuals using the nearest neighbor classifier. The accuracy up to 98.584% has been obtained when using 4 samples per class for training. The experimental results demonstrate that our proposed approach is feasible and effective in biometrics.     

一种基于特征不变描述的图像无缝拼接算法

针对尺度变化不明显场景的拼接,提出一种基于特征不变描述的图像无缝拼接算法.利用Harris特征检测算子进行特征点提取,在此基础上对提取出的特征点采用SIFT描述子进行处理,使其具备旋转不变性,然后利用k-d树算法进行遍历搜索定位,并用RANSAC算法进行图像间单应性变换矩阵计算,最后利用加权平均的融合方法进行图像无缝平滑,得到无缝拼接图像.实验结果表明:该算法在图像任意角度旋转的情况下,能有效地实现图像无缝拼接,并具有较强的鲁棒性.     

手掌静脉识别典型波长选择

目前的手掌静脉识别系统均采取主动光源来获取掌脉图像,光源波长的选择直接影响掌脉图像的清晰度与识别性能。典型的掌脉识别成像波长为760,850,890,940 nm,但没有指出哪种波长识别性能最佳。从两个角度解决此问题,从识别特征提取角度,建立了基于Fisher判别率的掌脉成像清晰度模型,对4种波长拍摄的掌脉清晰度进行比较;从特征匹配角度,以3种典型的生物特征识别算法对4种波长拍摄的掌脉图像进行识别性能比较。在包含4种波长共2400幅掌脉图像的自建图库中进行实验,模型选择和典型算法实验结果都表明,850 nm优于其他3种波长。证明了850 nm拍摄的掌脉图像的识别性能最佳。     

基于DSP的静脉识别系统

提出了一种基于ADSP-BF533的静脉识别系统设计方法。整个系统由静脉图像采集、静脉图像处理和识别两个模块组成。静脉图像由普通黑白模拟摄像机在近红外光照下获取;静脉图像处理和识别的核心单元是一颗ADI生产的Blackfin 533 DSP(ADSP-BF533),其速度可以满足后端处理的需要,可以实现静脉图像细化、特征提取及识别等功能。     

基于局部轮廓特征的无人机头部检测跟踪算法

针对无人机的结构特点,提出了一种基于目标轮廓提取、轮廓自动分段、头部定位以及头部模板匹配四个模块的目标头部检测跟踪算法.首先对第一帧图像提取目标轮廓,并通过计算轮廓点的变化率,对轮廓进行自动分段,得到目标的4个局部轮廓点列,进而根据头部轮廓点列的特点,完成头部轮廓筛选,然后利用基于目标中轴的二次曲线拟合,实现头部顶点的...     

A multi-resolution wavelet algorithm for hand vein pattern recognition

A novel hand vein recognition algorithm is developed based on multi-resolution wavelet analysis. The texture feature of hand vein can be extracted by three-level wavelet decomposition. Furthermore, Knearest neighbor (KNN) with support vector machines (SVM) and minimum distance classifier (MDC) are employed for feature matching. Finally, the experiments are respectively performed in identification and verification modes using Tianjin University (TJU) hand vein image database constructed by our group.The results show the feasibility and effectiveness of the proposed method.     

一种声图直航段数据自动提取及镶嵌的方法

声图镶嵌是利用成像声纳获得声图进行测深、水下地形地貌测绘的重要应用方向。常见的成像声纳多要求声纳载体做直线运动,而实际应用中载体有大量转弯的情况。为此提出了一种声图直航段数据自动提取方法,该方法首先利用Douglas-Peucker算法对声纳航迹进行抽稀处理,之后利用相邻抽稀点之间的距离判断数据是否为直航段,最后将直航段图像提取出来。获得直航段数据后,利用地理信息对声图进行镶嵌处理。对千岛湖湖底地貌图像进行了处理,获得了较好的镶嵌结果。