基于多模态生物识别的安全身份认证技术

本文分析了传统身份认证方法在电子取证中存在的问题,突出了生物特征识别技术应用于电子取证中的优点。针对单模态生物特征技术存在识别精度不够等问题,提出了将多模态生物特征技术的安全身份认证的体系结构,并探讨了多种特征信息融合的方法。[编者按]     

基于三角范数的多模态手指生物特征的分数层融合方法

多模态的生物特征融合已成为目前生物识别研究领域的主要发展趋势,从防伪性角度出发,满足普适性和易采集、易接受性的应用需求,提出了基于手指静脉,并结合指纹、指关节纹和指形的分数层融合来实现多模态生物特征的身份认证方案。实验结果表明,本文提出基于Sugeno-Weber三角范数的分数层融合方法,能够增大类内与类间匹配分数分布间的距离,提高了多模态生物特征的身份认证性能。     

多模态生物特征提取及相关性评价综述

生物特征识别是身份认证的重要手段,特征提取技术在其中扮演了关键角色,直接影响识别的结果。随着特征提取技术日趋成熟,学者们逐渐将目光投向了生物特征间的相关性问题。本文以单模态和多模态生物识别中的特征提取方法为研究对象,回顾了人脸与指纹的特征提取方法,分析了基于经验知识的特征分类提取方法以及基于深度学习的计算机逻辑采样提取方法,并从图像处理的角度对单模态与多模态方法进行对比。以当前多模态生物特征提取方法和DNA表达过程为引,提出了不同模态的生物特征之间存在相关性的猜想,以及对这一猜想进行建模的思路。在多模态生物特征提取的基础上,对今后可能有进展的各生物特征之间的相关性建模进行了展望。     

人脸识别的市场和应用分析

生物识别技术是利用人体生物特征进行身份认证的一种技术,人脸识别以其完全非接触和直观的特点,成为生物识别当中颇受关注的识别方式之一。     

DTW在线手写签名认证系统的研究

随着计算机网络技术和生物识别技术的发展,通过生物特征进行身份认证成为信息时代的需要.由于长久以来作为授权标志,手写签名是最容易被大众接受的身份认证方式之一.本文改进了经典DTW中距离的计算方法,在考虑了时间序列自身形状特征的基础上,解决了在线手写签名中时间序列非线性弯曲的对正问题.经过签名认证实验表明,当ERR为3%时,签名认证的效果最好,进而证明在线手写签名适合作为身份认证手段.     

基于行为足迹的多模态融合身份认证

针对单模态身份认证方法存在特征单一容易被伪造和攻破的问题,提出基于用户行为足迹的多模态特征融合隐式身份认证方法。在移动设备中采集用户使用设备时的触摸压力、触摸轨迹、加速度等传感器数据,利用特征选择技术提取触摸屏交互、移动模式、物理位置等特征并对其进行训练与融合,最终通过多模态特征融合模型实现用户身份认证。实验结果表明,该方法采用的特征级融合和决策级融合方式均获得了98%以上的认证准确率,相比单模态身份认证方法更难以被伪造和攻破,且认证准确率更高、稳定性更强。     

多模态生物特征信息安全防护体系研究

在新的计算能力和深度学习技术推动下,人工智能、大数据发展进入了繁荣期,导致多模态生物特征信息迅猛增加与应用.由于多模态生物识别具有自然性和多场景应用性,特征信息的采集、识别、分析不仅涉及个人隐私和人格尊严,还主动或被动暴露在现实环境中,高校面临着巨大的信息安全保护需求和风险挑战.通过对高校多模态生物特征信息安全问题及现...     

基于指纹和声纹的身份认证技术研究

基于生物特征识别的身份认证技术已经应用于多个领域,然而单一的生物特征有各自的优缺点,为了提高身份认证的安全性和鲁棒性,对多生物特征进行融合便成为了身份认证技术新的研究方向。将指纹识别和声纹识别通过加权融合的方法在匹配层进行融合,实验结果表明,融合系统的等错误率(EER)比指纹识别和声纹识别提高了0.3%~0.4%,证明了融合系统识别率有所提高。     

生物特征信息处理开发包BITK及其应用平台

由于人类固有的生物特征能用来进行可靠的身份认证和识别,近10年来生物特征识别已经成为研究热点.为了对生物特征识别研究提供软件支持,设计研发了生物特征信息处理开发包 (Biometric Information Processing Toolkit,BITK).BITK是一个C 软件开发包.它以非线性数据流模型来组织整体计算流程,提供了一个可扩展、可重用的框架来整合生物特征识别领域的算法和数据结构.BITK还设计了一个精干的可视化框架以及一个管理各种生物特征采集仪的一致性框架.此外,在BITK基础上研发了生物特征信息处理平台 (BITK-based Application Platform,BITKAPP).该平台通过灵活的plug-in架构和友好的用户界面,充分发挥BITK的功能,并降低了BITK的使用门槛.在实际应用中,BITK和BITKAPP向研究人员提供了一套高效率的研究、实验及开发手段,并且作为支撑平台完成了第一届生物特征识别竞赛(the 1st Biometric Verification Competition)的多模态数据采集任务.     

USB Key身份认证技术及其在电子商务活动中的应用研究

USB Key身份认证技术是与用户名加口令、生物特征识别技术并列的三大认证技术之一,是近几年发展起来的一种方便、快捷、安全的身份认证技术。它结合了现代密码学技术、智能卡技术和USB技术的一种新型身份识别技术。本文对当前USB Key身份认证技术进行了分析,并对其的相关应用进行了探讨,希望能够对我们认识和了解USB Key身份认证技术有所帮助。     

Enhancement of multimodal biometric segregation using unconstrained cohort normalisation

This paper presents an investigation into the effects, on the accuracy of multimodal biometrics, of introducing unconstrained cohort normalisation (UCN) into the score-level fusion process. Whilst score normalisation has been widely used in voice biometrics, its effectiveness in other biometrics has not been previously investigated. This study aims to explore the potential usefulness of the said score normalisation technique in face biometrics and to investigate its effectiveness for enhancing the accuracy of multimodal biometrics. The experimental investigations involve the two recognition modes of verification and open-set identification, in clean mixed-quality and degraded data conditions. Based on the experimental results, it is demonstrated that the capabilities provided by UCN can significantly improve the accuracy of fused biometrics. The paper presents the motivation for, and the potential advantages of, the proposed approach and details the experimental study.     

安全人脸识别解决方案研究

人脸面部特征,与生俱来,具有唯一性、自然性、终身不变等特点,因此人脸识别作为一种身份鉴别方式,相比于传统的认证技术具有巨大的便利性优势.然而人脸识别容易受到图片、视频、面具等伪造攻击,由于其不可更改特性,若生物特征发生泄漏或篡改,会造成难以挽回的风险和损失.本文提出的安全人脸识别解决方案,通过特殊的安全人脸采集模组,完成活体检测,模组中通过人脸加密专用密钥,对图片进行加密、签名处理,同时在识别流程中的多重安全设计,保证人脸生物特征的安全.     

Multimodal biometrics: Empirical study of performance-throughput trade-off

The paper briefly describes results of empirical study on performance (as measured by ROC) and throughput (as measured by number of matches per sec) of multimodal biometrics. We use cascaded multimodal biometric identification. Experiments show that cascaded multimodal biometric fusion improves both throughput and performance.     

Adaptive management of multimodal biometrics fusion using ant colony optimization

This paper presents a new approach for the adaptive management of multimodal biometrics to meet a wide range of application dependent adaptive security requirements. In this work, ant colony optimization (ACO) is employed for the selection of key parameters like decision threshold and fusion rule, to ensure the optimal performance in meeting varying security requirements during the deployment of multimodal biometrics systems. Particle swarm optimization (PSO) has been widely utilized for the optimal selection of these parameters in the earlier attempts in the literature [Veeramachaneni et al., 2005] and [Kumar et al., 2010]. However, in PSO these parameters are computed in continuous domain while they are assumed to be better represented as discrete variables [Kumar et al., 2010]. This paper therefore proposes the use of ACO, in which discrete biometric verification parameters are computed to ensure the optimal performance from the multimodal biometrics system. The proposed ACO based framework is also extended to the pattern classification approach where fuzzy binary decision tree (FBDT) is utilized for two-class biometrics verification. The experimental results are presented on true multimodal systems from various publicly available databases; IITD databases of palmprint and iris, XM2VTS database of speech and faces, and the NIST BSSR1 databases of faces and fingerprint images. Our experimental results presented in this paper suggest that (i) ACO based approach is capable of operating on significantly small error rates in comparison to the widely employed PSO for automated selection of biometrics fusion rules/parameters, (ii) the score-level fusion yields better performance with lower error rate in comparison to the decision level fusion, and finally (iii) the FBDT based classification approach delivers considerably superior performance for the adaptive biometrics verification.     

鉴别矢量增强在人耳人脸多模态识别中的应用

人耳识别与人脸识别在生物特征识别领域中占有重要位置,然而,剧烈的姿态变化一直是阻碍它们在现实生活中应用的瓶颈,提出一种鉴别矢量增强算法,以解决姿态人耳和姿态人脸图像的识别问题。为了考察多模态识别的可行性和有效性,利用串联、并联（广义主元分析）和典型相关分析等融合策略,将强化后的人耳、人脸鉴别矢量进行有效融合,通过最近邻方法进行分类识别。实验结果表明,鉴别矢量强化算法可以显著提高姿态人耳或是姿态人脸单生物特征的识别率,而多模态方法又会表现出更好的识别性能。     

FEATURES-LEVEL FUSION OF FACE AND HANDWRITTEN SIGNATURE IN MULTIMODAL BIOMETRIC IDENTIFICATION SYSTEM

Biometrics is an emerging tool used to identify humans by their physical and/or behavioral characteristics. This article presents a novel neural network–based approach for features-level fusion in a multimodal biometric identification system by combining both physical (human face) and behavioral (handwritten signature) traits. A single biometrics system has the weakness of providing neither 100% identification nor a 0% false accept rate (FAR)/false reject rate (FRR). One solution to this is to combine different biometrics together to get a multimodal biometric identification system. Moreover, a multimodal system is also robust in providing security against spoof attacks. Images of 32 × 32 pixels are used to eliminate bulk storage and processing requirements.     

Biometrics in Identity Management Systems

Biometric technology - the automated recognition of individuals using biological and behavioral traits - has been presented as a natural identity management tool that offers "greater security and convenience than traditional methods of personal recognition." Indeed, many existing government identity management systems employ biometrics to assure that each person has only one identity in the system and that only one person can access each identity. Historically, however, biometric technology has also been controversial, with many writers suggesting that biometrics invade privacy, that specific technologies have error rates unsuitable for large-scale applications, or that the techniques "are useful to organizations that regulate the individual, but of little use where the individual controls identification and authorization." Here, I address these controversies by looking more deeply into the basic assumptions made in biometric recognition. I'll look at some example systems and delve into the differences between personal identity and digital identity. I'll conclude by discussing how those whose identity is managed with biometrics can manage biometric identity management.     

Situation awareness of cancelable biometric system

Recently, cancelable biometrics emerged as one of the highly effective methods of template protection. The concept behind the cancelable biometrics or cancelability is a transformation of a biometric data or extracted feature into an alternative form, which cannot be used by the imposter or intruder easily, and can be revoked if compromised. In this paper, we present a novel architecture for template generation in the context of situation awareness system in real and virtual applications. We develop a novel cancelable biometric template generation algorithm utilizing random biometric fusion, random projection and selection. Proposed random cross-folding method generate cancelable biometric template from multiple biometric traits. We further validate the performance of the proposed algorithm using a virtual multimodal face and ear database.