Two-factor authenticated key agreement protocol based on biometric feature and password

A new two-factor authenticated key agreement protocol based on biometric feature and password was proposed.The protocol took advantages of the user’s biological information and password to achieve the secure communication without bringing the smart card.The biometric feature was not stored in the server by using the fuzzy extractor technique,so the sensitive information of the user cannot be leaked when the server was corrupted.The authentication messages of the user were protected by the server’s public key,so the protocol can resist the off-line dictionary attack which often appears in the authentication protocols based on password.The security of the proposed protocol was given in the random oracle model provided the elliptic computational Diffie-Hellman assumption holds.The performance analysis shows the proposed protocol has better security.     

Optimal feature selection-based biometric key management for identity management system: Emotion oriented facial biometric system

Identity management systems with biometric key binding make digital transactions secure and reliable. A novel methodology is proposed to develop an intelligent key management system using facial emotions. Key binding with facial emotions makes use of an intrinsic user specific trait facilitating a more natural computer to human interaction. The proposed system utilizes metaheuristic swarm intelligence based optimization techniques to extract optimal features. The work demonstrates key binding by encrypting an image with a secret key bound to optimal features extracted from facial emotions. Efficiency and correctness of proposed key management is validated by successful decryption at receiving end with any one of the enrolled emotions given as input. Deer Hunting Optimization Algorithm and Chicken Swarm Optimization are merged to select optimal features from facial emotions. The derived algorithm is called Fitness Sorted Deer Hunting Optimization Algorithm with Rooster Update. Seven facial emotions — anger, disgust, fear, happiness, sadness, surprise and neutral are used to extract optimal features from Japanese Female Facial Expressions and Yale Facial datasets to train the neural network. Proposed work achieved better performance results over state-of-art optimization algorithms such as whale optimization algorithm, grey wolf optimization, chicken swarm optimization and deer hunting optimization algorithm. Accuracy of proposed model is 2.2% better than deer hunting optimization algorithm and 12.3% better than chicken swarm optimization for a key length 80.     

基于图像特征的易损水印技术

该文在 Yeung-Mintzer(1997)的方法基础上提出了一种新颖的易损水印技术。为解决原算法存在的安全问题,提出利用基于图像特征的混沌密钥控制易损水印的嵌入。理论分析和实验结果证明该算法可以有效地抵制由原算法所产生的攻击问题。由于水印在空域逐个像素地进行嵌入,所提出的算法具有良好的局部修改检测性能。     

基于数学形态学的透射激光散斑多尺度特征分析

本文通过对透射情况下所采集的不同样品浓度的激光散斑图样颗粒尺度分布和平均值的计算,发现散斑具有多尺度分布的特征,且散斑颗粒平均尺寸的大小随着样品浓度的降低,即散射系数的降低而增大,与范西特一泽尼克定理相一致.     

SkyWing:开生物识别软件之先河--北京优利华通科技有限公司副总经理翟震宇访谈录

近年来,在发生了几次大的网络安全事故以后,网络安全问题日益引起人们,特别是计算机用户的重视。随着网络安全软件市场需求的进一步增大,国内网络安全企业如雨后春笋般出现。在这些网络安全企业中,有一家企业针对网络安全推出了具有世界先进水平的生物识别的解决方案,即SkyWing天翼网络身份指纹识别软件。这家企业就是北京优利华通科技有限公司(以下简称优利华通公司)。天翼软件开发的背景是什么?公司技术研发的优势有哪些?SkyWing产品有何特点?带着这些问题,记者采访了优利华通公司副总经理翟震宇。记者:谈到网络安全,业内人士大多知道它…     

基于自适应并行结构的多模态生物特征识别

传统多模态生物特征识别方法当出现生物特征缺失时,识别性能会明显下降。针对此问题,提出一种融合人脸、虹膜和掌纹的自适应并行结构多模态生物识别方法。该方法在设计融合策略时,考虑到所有可能的输入缺失,构造并行结构的融合函数集,在实际应用时根据输入状态自适应的选择融合策略进行识别。实验仿真结果表明该方法既可提高识别可靠性又可实现当有生物特征缺失时的性能稳定。     

一种基于集成学习和特征融合的遥感影像分类新方法

针对多源遥感数据分类的需要,提出了一种基于全极化SAR影像、极化相干矩阵特征、光学遥感影像光谱和纹理的多种特征融合和多分类器集成的遥感影像分类新方法.对全极化PALSAR数据进行预处理和极化相干矩阵特征提取,利用灰度共生矩阵计算光学和SAR影像的对比度、逆差距、二阶距、差异性等纹理特征参数,并与光谱特征结合,形成6种组合策略.利用集成学习方法对随机森林分类器、子空间分类器、最小距离分类器、支持向量机分类器、反向传播神经网络分类器等分类器进行组合,对不同组合策略的遥感影像特征集进行分类.结果表明提出的基于多种特征和多分类器集成的新方法很好地利用了主被动遥感数据在不同地表景观类型提取上的潜力,综合了多种算法的优势,能够有效地提高总体精度和各类别的分类精度.     

基于生物特征和混沌映射的多服务器身份认证方案

基于密码的用户远程认证系统已被广泛应用,近年来的研究发现,单一口令系统容易遭受字典分析、暴力破解等攻击,安全性不高.生物特征与密码相结合的认证方式逐渐加入远程认证系统中,以提高认证系统的安全水平.但现有认证系统通常工作在单一服务器环境中,扩展到多服务器环境中时会遇到生物特征模板和密码容易被单点突破、交叉破解的问题.为了克服以上问题,提出了一种基于生物特征和混沌映射的多服务器密钥认证方案,该方案基于智能卡、密码和生物特征,可明显提高多服务器身份认证系统的安全性及抗密码猜解的能力.     

MCYT baseline corpus: a bimodal biometric database

The current need for large multimodal databases to evaluate automatic biometric recognition systems has motivated the development of the MCYT bimodal database. The main purpose has been to consider a large scale population, with statistical significance, in a real multimodal procedure, and including several sources of variability that can be found in real environments. The acquisition process, contents and availability of the single-session baseline corpus are fully described. Some experiments showing consistency of data through the different acquisition sites and assessing data quality are also presented.     

Geo-localization based on CNN feature matching

A geo-localization method is proposed for military and civilian applications, which is used when no global navigation satellite system (GNSS) information is available. The open graphics library (OpenGL) is used to build a three-dimensional geographic model of the test area using digital elevation model (DEM) data, and the skyline can thus be extracted with the model to form a database. Then, MultiSkip DeepLab (MS-DeepLab), a fully convolutional semantic segmentation network with multiple skip structures, is proposed to extract the skyline from the query image. Finally, a matching model based on convolutional neural network (CNN) feature is adopted to calculate the similarity between the skyline features of the query image and the DEM database to realize automatic geo-localization. The experiments are conducted at a 202.6 km2 test site in north-eastern Changsha, China. 50 test points are selected to verify the effectiveness of the proposed method, and an excellent result with an average positioning error of 49.29 m is obtained.     

一种基于特征的自适应水印算法

基于图像多尺度空间理论和扩频机制以及视觉感知模型的特性,给出一种基于特征的数字图像水印算法。算法采用尺度不变特征变换算子提取图像的局部不变特征区域,根据信噪比特点自适应选取水印嵌入强度因子,将一幅二值水印图像嵌入到原始图像中,实现了数字水印的不可感知性和鲁棒性。仿真结果表明,该算法对添加噪声、压缩、旋转等常见的图像处理攻击具有较强的鲁棒性。     

基于特征融合的手势识别

在手势识别的过程中,手势的多样性和复杂性会对识别的可靠性和准确性带来较大影响.基于视觉的手势识别通常采取单一特征用于手势分类,但是单一特征无法较好地描述整个图像.因此本文提出多种特征融合的方法,分别提取改进后的梯度方向直方图(HOG)特征和MB-LBP特征,并进行特征融合,结合支持向量机(SVM)分类器完成手势图像的识别.实验结果表明,提取的融合特征包含手势图像的局部区域梯度信息和图像的纹理信息,可以更加全面地描述图像的手势特征.相较于单一特征识别方法而言,基于特征融合的方法有着更高的识别率.     

基于视觉特征的图像检索重排序

主要介绍了在基于关键字的图像检索结果上,利用视觉特征对图像进行重排序。由于关键字对图像的描述存在一定的偏差,所以检索结果难免存在偏差。尽管如此,基于关键字的检索结果中依然有一定比例的图片是与用户期望相关的,利用这一相关性可以建立一个由图像视觉特征描述的用户目标概念,以此作为基准采用分段插入排序对基于关键字的图像检索结果进行重排序,此方法既提高了检索准确率,又能满足实时性要求。文中介绍的方法采用了两种视觉特征,颜色直方图和局部二值模式(LBP)。     

一种基于共线特征点的线阵相机内参标定方法

提出一种利用共线的标定特征点确定线阵相机内参的方法。所有标定特征点均在线阵相机的视平面内。首先,标定过程中对标定特征点逐一成像,直接得到标定特征点和其对应像点,解决了空间标定点与像点的对应问题;其次,通过数学建模得到线阵相机的成像模型,联立多个位置处的成像模型解算出相机内参;最后,对影响线阵相机标定的因素进行分析及实验验证。理论分析和实验结果表明,文中的线阵相机标定方法简单灵活,无需制作精密的靶标,可获得大量标定点,提高了线阵相机标定的准确性和稳定性,实验得到成像特征点重投影像点位置偏差均方根为0.37 pixel。     

一种新的基于指纹与人脸特征级融合的模糊金库方案

针对基于生物特征的模糊金库易受相关攻击导致密钥和生物特征模板丢失以及基于单生物特征的模糊金库的认证性能不可靠的问题,提出了一种新的基于指纹与人脸特征级融合的模糊金库方案。该方案对指纹特征与人脸特征分别进行不可逆变换,并基于Diffie-Hellman算法在特征级变换后将指纹与人脸特征融合为一个模板。最后,将所得的融合模板用来构建模糊金库,通过更新随机矩阵使金库具备可撤销特性,有效抵御相关攻击,实现可靠的身份认证。实验结果表明,本文方案提高了系统的可靠性和多生物特征模板的安全性。     

局部和全局特征融合的红外图像显著性检测

为了更好地凸显复杂环境的红外目标特征,提出 一种融合局部和全局特征的红外图像 显著性检测方法。在获取图像超像素的基础上,提取每个区域空间距离加权的邻域对比度特 征,并考虑区域大小和位置的影响,构建局部显著图;然后提取每个区域空间距离加权的全 局灰度特征,构建全局显著图;最后融合局部和全局显著图,实现图像显著性检测。实验结 果 表明,本文方法的显著图结果目标区域一致高亮且边缘清晰,同时背景杂波抑制效果好。无 论 主观评价还是客观指标,本文方法都优于当前流行的图像显著性检测方法。     

Vehicle Tracking and Speed Measurement system (VTSM) based on novel feature descriptor: Diagonal Hexadecimal Pattern (DHP)

Object detection and tracking is an important and active research area in computer vision community. The proposed Vehicle Tracking and Speed Measurement (VTSM) system can find out speed parameters of the vehicles. Speed parameters are used to take judgment on accidents at a low cost. The main objective of this paper is to develop an algorithm that can detect foreground, track specified object and calculate speed parameter of the object. Identifying stationary background from moving objects in a video is a critical task. To achieve superior foreground detection quality across unconstrained scenarios, a novel dynamic background subtraction and object tracking algorithm using a novel Diagonal Hexadecimal Pattern (DHP) is proposed. Metric F-score and MOTA are used to measure the performance of the proposed system. From the results, it is observed that the proposed system gives good results for the background subtraction and tracking.     

Two-factor ( biometric and password) authentication keyexchange on lattice based on key consensus

In the post-quantum era, the password-based authentication key exchange (PAKE) protocol on lattice has the characteristics of convenience and high efficiency, however these protocols cannot resist online dictionary attack thatis a common method used by attackers. A lattice-based two-factor ( biometric and password) authentication keyexchange (TFAKE) protocol based on key consensus (KC) is proposed. The protocol encapsulates the hash valueof biometric information and password through a splittable encryption method, and compares the decapsulatedinformation with the server's stored value to achieve the dual identity authentication. Then the protocol utilizes theasymmetric hash structure to simplify the calculation steps, which increases the calculation efficiency. Moreover,KC algorithm is employed in reducing data transmission overhead. Compared with the current PAKE protocol, theproposed protocol has the characteristics of hybrid authentication and resisting online dictionary attack. And itreduces the number of communication rounds and improves the efficiency and the security of protocol application.     

基于局部特征匹配的目标跟踪研究

针对目标跟踪中的特征提取和匹配问题进行分析,提出了一种基于局部特征匹配的目标跟踪方法,该算法基于Shape Context进行特征提取。首先,对现有特征提取算法进行简单介绍,并详细介绍Shape Context的基本思想,基于此提出基于局部特征的跟踪算法。其次,详细阐述了目标跟踪算法：采用目标点的χ2-test直方图距...