基于特征融合的步态识别算法研究

根据人体步态变化特点,提出一种基于特征融合和神经网络的步态识别算法。首先采用时域差分法对运动人体轮廓进行分割,然后分别提取空间特征和频率特征,将两步态特征融合在一起,从而实现步态的分类和识别。在CASIA步态数据库上进行仿真实验,仿真结果表明,该方法不仅克服了单一特征提取方法存在的缺陷,同时提高了步态识别正确率。     

Fractal dimension applied to plant identification

This article discusses methods to identify plants by analysing leaf complexity based on estimating their fractal dimension. Leaves were analyzed according to the complexity of their internal and external shapes. A computational program was developed to process, analyze and extract the features of leaf images, thereby allowing for automatic plant identification. Results are presented from two experiments, the first to identify plant species from the Brazilian Atlantic forest and Brazilian Cerrado scrublands, using fifty leaf samples from ten different species, and the second to identify four different species from genus Passiflora, using twenty leaf samples for each class. A comparison is made of two methods to estimate fractal dimension (box-counting and multiscale Minkowski). The results are discussed to determine the best approach to analyze shape complexity based on the performance of the technique, when estimating fractal dimension and identifying plants.     

基于投影和小波分析的手指指节折痕识别算法

鉴于人体的手指指节折痕具有稳定性且因人而异的特点,该文提出一种基于投影和小波分析的手指指节折痕识别的新算法。对手指图像进行定位,经分割、归一化后得到了用于身份鉴别的手指子图。将手指子图向水平轴投影,得到含有折痕信息的一维信号,利用小波的多分辨率特点提取折痕信息进而形成代表折痕的特征矢量。在手指图像数据库中,利用最近邻分类器进行了算法验证,等错误率约为1.5%,实验结果表明了算法的有效性。     

Biometrics:Standing Throughout Emerging Technologies

Biometrics technologies have been around for quite some time and many have been deployed for different applications all around the world, ranging from small companies' time and attendance systems to access control systems for nuclear facilities. Biometrics offer a reliable solution for the establishment of the distinctiveness of identity based on who an individual is, rather than what he or she knows or carries. Biometric Systems automatically verify a person's identity based on his/her anatomical and behav...     

A Proposed Biometric Authentication Model to Improve Cloud Systems Security

Most user authentication mechanisms of cloud systems depend on the credentials approach in which a user submits his/her identity through a username and password. Unfortunately, this approach has many security problems because personal data can be stolen or recognized by hackers. This paper aims to present a cloud-based biometric authentication model (CBioAM) for improving and securing cloud services. The research study presents the verification and identification processes of the proposed cloud-based biometric authentication system (CBioAS), where the biometric samples of users are saved in database servers and the authentication process is implemented without loss of the users’ information. The paper presents the performance evaluation of the proposed model in terms of three main characteristics including accuracy, sensitivity, and specificity. The research study introduces a novel algorithm called “Bio_Authen_as_a_Service” for implementing and evaluating the proposed model. The proposed system performs the biometric authentication process securely and preserves the privacy of user information. The experimental result was highly promising for securing cloud services using the proposed model. The experiments showed encouraging results with a performance average of 93.94%, an accuracy average of 96.15%, a sensitivity average of 87.69%, and a specificity average of 97.99%.     

Dual-key-binding cancelable palmprint cryptosystem for palmprint protection and information security

Biometric cryptosystems and cancelable biometrics are both practical and promising schemes to enhance the security and privacy of biometric systems. Though a number of bio-crypto algorithms have been proposed, they have limited practical applicability because they lack of cancelability. Since biometrics are immutable, the users whose biometrics are stolen cannot use bio-crypto systems anymore. Cancelable biometric schemes are of cancelability; however, they are difficult to compromise the conflicts between the security and performance. By embedded a novel cancelable palmprint template, namely “two dimensional (2D) Palmprint Phasor”, the proposed palmprint cryptosystem overcomes the lack of cancelability in existing biometric cryptosystems. Besides, the authentication performance is enhanced when users have different tokens/keys. Furthermore, we develop a novel dual-key-binding cancelable palmprint cryptosystem to enhance the security and privacy of palmprint biometric. 2D Palmprint Phasor template is scrambled by the scrambling transformation based on the chaotic sequence that is generated by both the user's token/key and strong key extracted from palmprint. Dual-key-binding scrambling not only has more robustness to resist against chosen plain text attack, but also enhances the secure requirement of non-invertibility. 2D Palmprint Phasor algorithm and dual-key-binding scrambling both increase the difficulty of adversary's statistical analysis. The experimental results and security analysis confirm the efficiency of the proposed scheme.     

基于击键压力和时间匹配的异常检测方法

为了有效利用用户的生物特征进行入侵者身份识别,提出了一种基于用户击键特征进行异常检测的新方法.该方法根据人们在击键时所产生的按键压力和时间间隔的惟一性,利用正态分布的特性控制模式库生成方式,构造出能够描述每个用户独有特征的击键特征向量库,然后利用模式匹配算法对新登陆用户进行检测.相关实验验证了该方法具有较高的用户识别能力.     

FaceEncAuth：基于FaceNet和国密算法的人脸识别隐私安全方案

人脸识别中,人脸特征作为生物特征的一种,具有唯一性、不可撤销性,一旦遭到攻击、篡改或泄露,用户隐私安全将面临巨大威胁。针对这一问题,提出一种基于深度学习和加密算法的人脸识别隐私安全方案。该方案中,利用FaceNet深度学习算法来高效提取人脸特征,协调生物特征模糊性与密码系统的精确性,采用CKKS全同态加密算法进行人脸识别密文域的运算,通过国密SM4算法增强人脸特征密文抵抗恶意攻击的能力,利用其对称密码的性质兼顾了安全性和运算效率,而SM9非对称密码算法则用于SM4算法对称密钥的管理。实验结果及分析表明,该方案在不影响人脸识别准确率、效率的前提下提高了数据传输、存储和比对的安全性。     

基于EMD和SVM的虹膜识别方法

在目前的生物特征识别方法中,虹膜识别被认为是最可靠的技术。提出一种基于经验模态分解和支持向量机的虹膜识别方法——EMD提取虹膜特征,SVM实现模式匹配。实验结果表明,该方法能够有效地应用到身份鉴别系统中。