结构特征下的可撤销人脸识别

目的 相对于其他生物特征识别技术,人脸识别具有非接触、不易察觉和易于推广等特点,在公共安全和日常生活中得到广泛应用。在移动互联网时代,云端人脸识别可以有效地提高识别精度,但是需要将大量的人脸数据上传到第三方服务器。由于人的面部特征是唯一的,一旦数据库泄露就会面临模板攻击和假冒攻击等安全威胁。为了保证人脸识别系统的安全性并提高其识别率,本文提出一种融合人脸结构特征的可撤销人脸识别算法。方法 首先,对原始人脸图像提取结构特征作为虚部分量,与原始人脸图像联合构建复数矩阵并通过随机二值矩阵进行置乱操作。然后,使用2维主成分分析方法将置乱的复数矩阵映射到新的特征空间。最后,采用基于曼哈顿距离的最近邻分类器计算识别率。结果 在4个不同人脸数据库上的实验结果表明,原始人脸图像和结构特征图像经过随机二值矩阵置乱后,人眼无法察觉出有用的信息且可以重新生成,而且融合方差特征后,在GT （Georgia Tech）、NIR （Near Infrared）、VIS （Visible Light）和YMU （YouTuBe Makeup）人脸数据库上,平均人脸识别率分别提高了4.9%、2.25%、2.25%和1.98%,且平均测试时间均在1.0 ms之内,表明该算法实时性强,能够满足实际应用场景的需求。结论 本文算法可在不影响识别率的情况下保证系统的安全性,满足可撤销性。同时,融合结构特征丰富了人脸信息的表征,提高了人脸识别系统的识别率。     

From scores to face templates: a model-based approach

Regeneration of templates from match scores has security and privacy implications related to any biometric authentication system. We propose a novel paradigm to reconstruct face templates from match scores using a linear approach. It proceeds by first modeling the behavior of the given face recognition algorithm by an affine transformation. The goal of the modeling is to approximate the distances computed by a face recognition algorithm between two faces by distances between points, representing these faces, in an affine space. Given this space, templates from an independent image set (break-in) are matched only once with the enrolled template of the targeted subject and match scores are recorded. These scores are then used to embed the targeted subject in the approximating affine (non-orthogonal) space. Given the coordinates of the targeted subject in the affine space, the original template of the targeted subject is reconstructed using the inverse of the affine transformation. We demonstrate our ideas using three, fundamentally different, face recognition algorithms: Principal Component Analysis (PCA) with Mahalanobis cosine distance measure, Bayesian intra-extrapersonal classifier (BIC), and a feature-based commercial algorithm. To demonstrate the independence of the break-in set with the gallery set, we select face templates from two different databases: Face Recognition Grand Challenge (FRGC) and Facial Recognition Technology (FERET) Database (FERET). With an operational point set at 1 percent False Acceptance Rate (FAR) and 99 percent True Acceptance Rate (TAR) for 1,196 enrollments (FERET gallery), we show that at most 600 attempts (score computations) are required to achieve a 73 percent chance of breaking in as a randomly chosen target subject for the commercial face recognition system. With similar operational set up, we achieve a 72 percent and 100 percent chance of breaking in for the Bayesian and PCA based face recognition systems, respectively. With three different levels of score quantization, we achieve 69 percent, 68 percent and 49 percent probability of break-in, indicating the robustness of our proposed scheme to score quantization. We also show that the proposed reconstruction scheme has 47 percent more probability of breaking in as a randomly chosen target subject for the commercial system as compared to a hill climbing approach with the same number of attempts. Given that the proposed template reconstruction method uses distinct face templates to reconstruct faces, this work exposes a more severe form of vulnerability than a hill climbing kind of attack where incrementally different versions of the same face are used. Also, the ability of the proposed approach to reconstruct actual face templates of the users increases privacy concerns in biometric systems.     

非负低秩图嵌入算法

现有的非负矩阵分解方法(NMF)还存在一些不足之处。一方面,NMF方法直接在高维原始图像数据集上计算它的低维表示,而实际上原始图像数据集的有效信息常常隐藏在它的低秩结构中;另一方面,NMF方法还存在对噪声数据和不可靠图敏感以及鲁棒性差的缺点。为了解决这些问题,提出了一种非负低秩图嵌入算法(NLGE),该算法同时考虑了原始图像数据的几何信息和有效低秩结构,使得其鲁棒性有了进一步的提高。此外,还给出了一种求解NLGE算法的迭代规则,并进一步证明了该求解算法的收敛性。最后,在ORL、CMU PIE、YaleB和USPS数据库上的实验结果表明了NLGE算法的有效性。     

Multi-PIE

A close relationship exists between the advancement of face recognition algorithms and the availability of face databases varying factors that affect facial appearance in a controlled manner. The CMU PIE database has been very influential in advancing research in face recognition across pose and illumination. Despite its success the PIE database has several shortcomings: a limited number of subjects, a single recording session and only few expressions captured. To address these issues we collected the CMU Multi-PIE database. It contains 337 subjects, imaged under 15 view points and 19 illumination conditions in up to four recording sessions. In this paper we introduce the database and describe the recording procedure. We furthermore present results from baseline experiments using PCA and LDA classifiers to highlight similarities and differences between PIE and Multi-PIE.     

Biometric template protection using cancelable biometrics and visual cryptography techniques

Wide spread use of biometric based authentication implies the need to secure biometric reference data. Various template protection schemes have been introduced to prevent biometric forgery and identity thefts. Cancelable biometrics and visual cryptography are two recent technologies introduced to address the concerns regarding privacy of biometric data, and to improve public confidence and acceptance of biometric systems. Cancelable biometrics is an important technique that allows generation of revocable biometric templates. As the number of biometric instances are limited and once compromised they are lost forever. Cancelable biometrics allows templates to be cancelled and revoked like passwords innumerable times. Recently, various approaches that utilize visual cryptography to secure the stored template and impart privacy to the central databases have been introduced. This work attempts to summarize the existing approaches in literature making use of these two technologies to protect biometric templates.     

Face Attribute Convolutional Neural Network System for Data Security with Improved Crypto Biometrics

Due to the enormous usage of the internet for transmission of data over a network, security and authenticity become major risks. Major challenges encountered in biometric system are the misuse of enrolled biometric templates stored in database server. To describe these issues various algorithms are implemented to deliver better protection to biometric traits such as physical (Face, fingerprint, Ear etc.) and behavioural (Gesture, Voice, tying etc.) by means of matching and verification process. In this work, biometric security system with fuzzy extractor and convolutional neural networks using face attribute is proposed which provides different choices for supporting cryptographic processes to the confidential data. The proposed system not only offers security but also enhances the system execution by discrepancy conservation of binary templates. Here Face Attribute Convolutional Neural Network (FACNN) is used to generate binary codes from nodal points which act as a key to encrypt and decrypt the entire data for further processing. Implementing Artificial Intelligence (AI) into the proposed system, automatically upgrades and replaces the previously stored biometric template after certain time period to reduce the risk of ageing difference while processing. Binary codes generated from face templates are used not only for cryptographic approach is also used for biometric process of enrolment and verification. Three main face data sets are taken into the evaluation to attain system performance by improving the efficiency of matching performance to verify authenticity. This system enhances the system performance by 8% matching and verification and minimizes the False Acceptance Rate (FAR), False Rejection Rate (FRR) and Equal Error Rate (EER) by 6 times and increases the data privacy through the biometric cryptosystem by 98.2% while compared to other work.     

BinaryFace:基于深层卷积神经网络的人脸模板保护模型

随着生物识别技术的广泛应用,人们越来越担心生物模板信息的安全性和隐私性。为此人们提出很多生物模板信息的保护算法,但其一般需要牺牲可识别性来换取高安全性。为了在保证高安全性的同时尽可能提高可识别性,本文提出一种新的由特征转换和生物加密组成的二阶段人脸模板保护方案。在特征转换阶段,基于VGGFace提出一种新的基于卷积神经网络的BinaryFace网络,通过设计新的随机正交映射矩阵、量化损失函数和最大熵损失函数实现人脸模板的二进制转换。同时为了减少网络参数,设计新的深度可分离瓶颈卷积层,BinaryFace相比VGGFace在参数和浮点数（Flops）上分别减少约75%和约35%。在生物加密阶段,将人脸二进制模板转换中随机正交映射生成的纠错码输入模糊承诺方案,生成加密的人脸模板并存储到数据库中。在验证阶段,通过相同的流程恢复出纠错码,并与原始纠错码进行哈希校验得到最终的匹配结果。在评测阶段,本文提出的方法在CMU-PIE、FEI、Color FERET等3个数据集上,相比之前的工作在GAR上有约6.5%的提升,同时将EER降低了约4倍。     

Towards enhancing the security and accuracy of iris recognition systems

The intricate structure of the iris constitutes a powerful biometric characteristic utilized by iris recognition algorithms to extract discriminative biometric templates. Iris recognition is field-proven but consequential issues, e.g. privacy protection or recognition in unconstrained environments, still to be solved, raise the need for further investigations. In this paper different improvements focused on template protection and biometric comparators are presented. Experimental evaluations are performed on a public dataset confirming the soundness of proposed enhancements.     

基于L21范数的非负低秩图嵌入算法

现有的非负矩阵分解方法直接在原始高维图像数据集上计算低维表示,同时存在对噪声数据、噪声标签、不可靠图敏感及鲁棒性较差的缺点.为了解决上述问题,文中提出基于L21范数的非负低秩图嵌入算法(NLGEL21),同时考虑原始数据集的有效低秩结构和几何信息.在图嵌入和数据重构函数中引入L21范数,进一步提高鲁棒性,并给出求解NLGEL21的乘性迭代公式和收敛性证明.在ORL、CMU PIE、YaleB人脸数据库上的实验验证NLGEL21的优越性.     

加权模板匹配的二值化阈值不敏感性研究

数字图像二值化处理过程中,阈值的选取非常之关键,为了在实际应用中能够快速准确地匹配出二值化图像中的目标图像,文中采用模板匹配的方法,对标准模板匹配算法和加权模板匹配算法的二值化阈值敏感性进行了研究。根据实验图像在二值化处理过程中所取阈值的波动对图像匹配结果的影响情况,得到加权模板匹配算法与标准模板匹配算法的二值化阈值敏感性差异。实验结论同时表明加权模板匹配算法具有较强的二值化阈值不敏感性和匹配性能好的优点。     

A review on performance,security and various biometric template protection schemes for biometric authentication systems

Identifying a person based on their behavioral and biological qualities in an automated manner is called biometrics. The authentication system substituting traditional password and token for authentication and relies gradually on biometric authentication methods for verification of the identity of an individual. This proves the fact that society has started depending on biometric-based authentication systems. Security of biometric authentication needs to be reviewed and discussed as there are multiple points related to integrity and public reception of biometric-based authentication systems. Security and recognition accuracy are the two most important aspects which must be considered while designing biometric authentication systems. During enrollment phase scanning of biometric data is done to determine a set of distinct biometric feature set known as biometric template. Protection of biometric templates from various hacking efforts is a topic of vital importance as unlike passwords or tokens, compromised biometric templates cannot be reissued. Therefore, giving powerful protection techniques for biometric templates and still at that very moment preparing great identification accuracy is a good research problem nowadays, as well as in the future. Furthermore, efficiency under non-ideal conditions is also supposed to be inadequate and thus needs special attention in the design of a biometric authentication system. Disclosure of various biometric traits in miscellaneous applications creates a severe compromise on the privacy of the user. Biometric authentication can be utilized for remote user authentication. In this case, the biometric data of users typically called templates are stored in a server. The uniqueness and stability of biometrics ended it useful over traditional authentication systems. But, a similar thing made the enduring harm of a user’s identity in biometric systems. The architecture of the biometric system leads to several hazards that lead to numerous security concerns and privacy threats. To address this issue, biometric templates are secured using several schemes that are categorized as biometric cryptosystems, cancelable biometrics, hybrid methods, Homomorphic Encryption, visual cryptography based methods. Biometric cryptosystems and cancelable biometrics techniques provide reliable biometric security at a great level. However, there persist numerous concerns and encounters that are being faced during the deployment of these protection technologies. This paper reviews and analyses various biometric template protection methods. This review paper also reflects the limitations of various biometric template protection methods being used in present times and highlights the scope of future work.

     

LDE融合光谱回归分类的光照变化人脸识别

针对光照变化人脸识别问题中传统的光谱回归算法不能很好地进行特征提取而严重影响识别性能的问题,提出了局部判别嵌入优化光谱回归分类的人脸识别算法。计算出训练样本的特征向量;借助于数据的近邻和分类关系,利用局部判别嵌入算法构建分类问题所需的嵌入,同时学习每种分类的子流形所需的嵌入;利用光谱回归分类算法计算投影矩阵,并利用最近邻分类器完成人脸的识别。在两大人脸数据库扩展YaleB及CMU PIE上的实验验证了该算法的有效性,实验结果表明,相比其他光谱回归算法,该算法取得了更高的识别率、更好的工作特性,并且降低了计算复杂度。     

Innovative Hetero-Associative Memory Encoder (HAMTE) for Palmprint Template Protection

Many types of research focus on utilizing Palmprint recognition in user identification and authentication. The Palmprint is one of biometric authentication (something you are) invariable during a person’s life and needs careful protection during enrollment into different biometric authentication systems. Accuracy and irreversibility are critical requirements for securing the Palmprint template during enrollment and verification. This paper proposes an innovative HAMTE neural network model that contains Hetero-Associative Memory for Palmprint template translation and projection using matrix multiplication and dot product multiplication. A HAMTE-Siamese network is constructed, which accepts two Palmprint templates and predicts whether these two templates belong to the same user or different users. The HAMTE is generated for each user during the enrollment phase, which is responsible for generating a secure template for the enrolled user. The proposed network secures the person’s Palmprint template by translating it into an irreversible template (different features space). It can be stored safely in a trusted/untrusted third-party authentication system that protects the original person’s template from being stolen. Experimental results are conducted on the CASIA database, where the proposed network achieved accuracy close to the original accuracy for the unprotected Palmprint templates. The recognition accuracy deviated by around 3%, and the equal error rate (EER) by approximately 0.02 compared to the original data, with appropriate performance (approximately 13 ms) while preserving the irreversibility property of the secure template. Moreover, the brute-force attack has been analyzed under the new Palmprint protection scheme.     

多窗口图像二值化算法研究

常用的全局二值法和局部二值法算法存在细节丢失、噪声引入、运算时间过长等弊端。为此提出了一种多窗口图像二值化算法,采用多窗口模板分别对图像进行简单二值化处理,对不同窗口处理下获得的二值图进行综合判断,最终确定每个像素点的逻辑值。通过MATLAB仿真,与常用二值化算法进行比较,验证提出的多窗口图像二值化算法具有处理简单、运算速度快、鲁棒性较好等优点。     

Cancelable features using log-Gabor filters for biometric authentication

Wide spread use of biometric based authentication requires security of biometric data against identity thefts. Cancelable biometrics is a recent approach to address the concerns regarding privacy of biometric data, public confidence, and acceptance of biometric systems. This work proposes a template protection approach which generates revocable binary features from phase and magnitude patterns of log-Gabor filters. Multi-level transformations are applied at signal and feature level to distort the biometric data using user specific tokenized variables which are observed to provide better performance and security against information leakage under correlation attacks. A thorough analysis is performed to study the performance, non-invertibility, and changeability of the proposed approach under stolen token scenario on multiple biometric modalities. It is revealed that generated templates are non-invertible, easy to revoke, and also deliver good performance.     

Linear discriminant projection embedding based on patches alignment

Dimensionality reduction is often required as a preliminary stage in many data analysis applications. In this paper, we propose a novel supervised dimensionality reduction method, called linear discriminant projection embedding (LDPE), for pattern recognition. LDPE first chooses a set of overlapping patches which cover all data points using a minimum set cover algorithm with geodesic distance constraint. Then, principal component analysis (PCA) is applied on each patch to obtain the data's local representations. Finally, patches alignment technique combined with modified maximum margin criterion (MMC) is used to yield the discriminant global embedding. LDPE takes both label information and structure of manifold into account, thus it can maximize the dissimilarities between different classes and preserve data's intrinsic structures simultaneously. The efficiency of the proposed algorithm is demonstrated by extensive experiments using three standard face databases (ORL, YALE and CMU PIE). Experimental results show that LDPE outperforms other classical and state of art algorithms.     

改进的自商图算法

针对人脸识别中的光照变化问题,提出一种改进的自商图算法。对光照图像进行伽玛变换,使用非下采样轮廓波变换对图像进行多尺度多方向分析,对各方向子带进行Wiener滤波,利用自商图模型提取人脸图像的光照不变特性。Yale B与CMU PIE人脸库上的实验结果表明,与传统算法相比,该算法的平均识别率更高。     

自适应半监督边界费舍尔分析

基于图的半监督算法已经成功地应用于人脸识别中,算法不仅考虑带标签数据而且利用一致性的假设。传统的算法一致性约束是定义在原特征空间中,但是在原特征空间中定义的一致性不是最好的。提出了自适应半监督边界费舍尔分析算法,它将一致性约束定义在原特征空间和期望低维特征空间中。在CMU PIE和YALE-B数据库上进行了实验,结果表明自适应半监督边界费舍尔分析算法在人脸识别率上有显著的提高。     

基于非凸低秩分解判别的叠加线性稀疏人脸识别

目的 针对因采集的人脸图像样本受到污染而严重干扰人脸识别及训练样本较少（小样本）时会由于错误的稀疏系数导致性能急剧下降从而影响人脸识别的问题,提出了一种基于判别性非凸低秩矩阵分解的叠加线性稀疏表示算法。方法 首先由γ范数取代传统核范数,克服了传统低秩矩阵分解方法求解核范数时因矩阵奇异值倍数缩放导致的识别误差问题;然后引入结构不相干判别项,以增加不同类低秩字典间的非相干性,达到抑制类内变化和去除类间相关性的目的;最后利用叠加线性稀疏表示方法完成分类。结果 所提算法在AR人脸库中的识别率达到了98.67±0.57%,高于SRC（sparse representation-based classification）、ESRC（extended SRC）、RPCA（robust principal component analysis）+SRC、LRSI（low rank matrix decomposition with structural incoherence）、SLRC（superposed linear representation based classification）-l₁等算法;同时,遮挡实验表明,算法对遮挡图像具有更好的鲁棒性,在不同遮挡比例下,相比其他算法均有更高的识别率。在CMU PIE人脸库中,对无遮挡图像添加0、10%、20%、30%、40%的椒盐噪声,算法识别率分别达到90.1%、85.5%、77.8%、65.3%和46.1%,均高于其他算法。结论 不同人脸库、不同比例遮挡和噪声的实验结果表明,所提算法针对人脸遮挡、表情和光照等噪声因素依然保持较高的识别率,鲁棒性更好。     

SDF classifier revisited

This paper is addressing problems related to the construction of classifiers based on the Similarity Discriminant Function (SDF), in which the traditional vector representation of a pattern is replaced with matrix data. We introduce potential modifications of the matrix data structure and propose new variants of the SDF. The algorithms that we present were tested on images of handwritten digits and on photographs of human faces, taken from the ORL and CMU‐PIE databases. The results of experiments show that our modifications significantly improved the performance of the original SDF classifier.