Online learning from local features for video-based face recognition

This paper presents an online learning approach to video-based face recognition that does not make any assumptions about the pose, expressions or prior localization of facial landmarks. Learning is performed online while the subject is imaged and gives near realtime feedback on the learning status. Face images are automatically clustered based on the similarity of their local features. The learning process continues until the clusters have a required minimum number of faces and the distance of the farthest face from its cluster mean is below a threshold. A voting algorithm is employed to pick the representative features of each cluster. Local features are extracted from arbitrary keypoints on faces as opposed to pre-defined landmarks and the algorithm is inherently robust to large scale pose variations and occlusions. During recognition, video frames of a probe are sequentially matched to the clusters of all individuals in the gallery and its identity is decided on the basis of best temporally cohesive cluster matches. Online experiments (using live video) were performed on a database of 50 enrolled subjects and another 22 unseen impostors. The proposed algorithm achieved a recognition rate of 97.8% and a verification rate of 100% at a false accept rate of 0.0014. For comparison, experiments were also performed using the Honda/UCSD database and 99.5% recognition rate was achieved.     

2D face recognition based on supervised subspace learning from 3D models

One of the main challenges in face recognition is represented by pose and illumination variations that drastically affect the recognition performance, as confirmed by the results of recent face recognition large-scale evaluations. This paper presents a new technique for face recognition, based on the joint use of 3D models and 2D images, specifically conceived to be robust with respect to pose and illumination changes. A 3D model of each user is exploited in the training stage (i.e. enrollment) to generate a large number of 2D images representing virtual views of the face with varying pose and illumination. Such images are then used to learn in a supervised manner a set of subspaces constituting the user's template. Recognition occurs by matching 2D images with the templates and no 3D information (neither images nor face models) is required. The experiments carried out confirm the efficacy of the proposed technique.     

Fusing cluster-centric feature similarities for face recognition in video sequences

The emergence of video has presented new challenges to the problem of face recognition. Most of the existing methods are focused towards the use of either representative exemplars or image sets to summarize videos. There is little work as to how they can be combined effectively to harness their individual strengths. In this paper, we investigate a new dual-feature approach to face recognition in video sequences that unifies feature similarities derived within local appearance-based clusters. Relevant similarity matching involving exemplar points and cluster subspaces are comprehensively modeled within a Bayesian maximum-a posteriori (MAP) classification framework. An extensive performance evaluation of the proposed method on three face video datasets have demonstrated promising results.     

基于分块非负矩阵分解人脸识别增量学习*

非负矩阵分解(NMF)算法可以提取图像的局部特征,然而NMF算法有两个主要缺点：a）当矩阵维数较大时,NMF算法非常耗时;b）当增加新的训练样本或类别时,NMF算法必须进行重复学习。为克服NMF算法这些缺点,提出了一种新的分块NMF算法(BNMF)。特别地,该方法还可用于增量学习。通过在FERET和CMU PIE人脸数据库上进行实验,结果表明该算法均优于NMF和PCA算法。     

Eigenspace updating for non-stationary process and its application to face recognition

In this paper, we introduce a novel approach to modeling non-stationary random processes. Given a set of training samples sequentially, we can iteratively update the eigenspace to manifest the current statistics provided by each new sample. The updated eigenspace is derived based more on recent samples and less on older samples, controlled by a number of decay parameters. Extensive study has been performed on how to choose these decay parameters. Other existing eigenspace updating algorithms can be regarded as special cases of our algorithm. We show the effectiveness of the proposed algorithm with both synthetic data and practical applications on face recognition. Significant improvements have been observed on face images with different variations, such as pose, expression and illumination variations. We expect the proposed algorithm to have other applications in active recognition and modeling as well.     

人脸识别活体检测研究方法综述

人脸识别具有广泛的应用,但容易受到伪造的欺骗人脸攻击而影响安全性,设计检测准确率高、泛化能力强、满足实时性需求的活体检测方法是目前的研究重点。将现有的人脸活体检测研究方法分为基于手工设计特征表达、基于深度学习和基于融合策略的方法,介绍每类方法所包含的典型算法的基本思想、实现步骤及优缺点。最后对已公开的人脸活体检测数据库进行整理说明,对人脸活体检测的发展趋势以及还需要进一步解决的问题进行综述,为今后人脸活体检测的研究提供参考和借鉴。     

视频人脸识别进展综述

人脸识别是生物特征识别领域的一项关键技术,长期以来得到研究者的广泛关注.视频人脸识别任务特指从一段视频中提取出人脸的关键信息,从而完成身份识别.相较于基于图像的人脸识别任务来说,视频数据中的人脸变化模式更为多样且视频帧之间存在较大差异,如何从冗长而复杂的视频中抽取到人脸的关键特征成为当前的研究重点.以视频人脸识别技术为...     

Intrapersonal subspace analysis with application to adaptive Bayesian face recognition

We propose a subspace distance measure to analyze the similarity between intrapersonal face subspaces, which characterize the variations between face images of the same individual. We call the conventional intrapersonal subspace the average intrapersonal subspace (AIS) because the image differences often come from a large number of persons. We call an intrapersonal subspace specific intrapersonal subspace (SIS) if the image differences are from just one person. We demonstrate that SIS varies from person to person and most SISs are not similar to AIS. Based on these observations, we introduce the maximum a posteriori (MAP) adaptation to the problem of SIS estimation, and apply it to the Bayesian face recognition algorithm. Experimental results show that the adaptive Bayesian algorithm outperforms the non-adaptive Bayesian algorithm as well as Eigenface and Fisherface methods when a small number of adaptation images are available.     

Orthogonal local spline discriminant projection with application to face recognition

In this paper, an efficient feature extraction algorithm called orthogonal local spline discriminant projection (O-LSDP) is proposed for face recognition. Derived from local spline embedding (LSE), O-LSDP not only inherits the advantages of LSE which uses local tangent space as a representation of the local geometry so as to preserve the local structure, but also makes full use of class information and orthogonal subspace to improve discriminant power. Extensive experiments on several standard face databases demonstrate the effectiveness of the proposed method.     

LDA/GE在人脸识别中的应用

基于谱图理论和流形学习,同时受FKT的启发,LDA算法可以进一步改进和化简。FKT已经被证明为二次判别分析中的低秩近似最优解,一开始只是用于二类识别问题,近年陆续有文章将它用于人脸识别中,以解决样本数小于样本维数的问题。LDA使用FKT求解的时候,在图嵌入的框架下可以转化为两次嵌入求解,第一次嵌入是PCA,第二次是由PCA的特征向量张成的空间中求判别式中分子的特征值分解问题。这样不仅去除了小样本问题下的奇异性困扰,更重要的是,基于谱图理论,将判别分析中的除法去掉了。最后,给出和其他方法比较的人脸识别实验结果和结论。     

半随机子空间的LDA人脸识别方法

小样本问题和对局部变化（如遮挡、表情、光照等）识别的不鲁棒性是线性判别分析（LDA）在处理人脸图像时所常面临的问题。针对LDA的这些不足,提出了一种基于LDA的半随机子空间方法（SemiRS-LDA）。与传统的基于整个人脸样本特征集采样的随机子空间方法不同的是,SemiRS-LDA将随机采样建立在人脸图像的子图像上。该方法首先将人脸图像集划分成若干个子图像集,然后将随机子空间方法应用于每个子图像集上并构建多个LDA分类器,最后使用投票方法将各分类器进行组合。在两个标准人脸数据库（AR、ORL）上进行了实验,结果表明了所提方法不仅能获得较高的识别性能,而且对图像的光线、遮挡等也具有较强的鲁棒性。     

Subspace distance analysis with application to adaptive Bayesian algorithm for face recognition

We propose subspace distance measures to analyze the similarity between intrapersonal face subspaces, which characterize the variations between face images of the same individual. We call the conventional intrapersonal subspace average intrapersonal subspace (AIS) because the image differences often come from a large number of persons. An intrapersonal subspace is referred to as specific intrapersonal subspace (SIS) if the image differences are from just one person. We demonstrate that SIS varies significantly from person to person, and most SISs are not similar to AIS. Based on these observations, we introduce the maximum a posteriori (MAP) adaptation to the problem of SIS estimation, and apply it to the Bayesian face recognition algorithm. Experimental results show that the adaptive Bayesian algorithm outperforms the non-adaptive Bayesian algorithm as well as Eigenface and Fisherface methods if a small number of adaptation images are available.     

基于特征化字典的低秩表示人脸识别

针对现有低秩表示（LRR）算法中全局与局部人脸特征信息融合不足的问题,提出了一种新的人脸识别算法——基于特征化字典的低秩表示（LRR-CD）。首先,将每张人脸照片表示成一个个特征化字典的集合,然后同时最小化基于训练样本的低秩重构特征系数以及与之相对应的类内特征差异。为了获得高效且具有高判别性的人脸图像的特征块重构系数矩阵,提出了一种新的数学公式模型,通过同时求解训练样本中相对应的特征块以及对应的类内特征差异词典的低秩约束问题,尽可能完整地保留原始高维人脸图像中的全局和局部信息,尤其是局部类内差异特征。另外,由于对特征块中信息的充分挖掘,所提算法对于一般程度上的面部遮挡和光照等噪声影响具有良好的鲁棒性。在AR、CMU-PIE和Extended Yale B人脸数据库进行多项对比实验,由实验结果可知LRR-CD相较于对比的稀疏表示（SRC）、协从表示（CRC）、低秩表示正规切（LRR-NCUT）和低秩递归最小二乘（LRR-RLS）算法在平均识别率上有2.58~17.24个百分点的提高。实验结果表明LRR-CD性能优于与之对比的算法,可以更高效地用于人脸全局和局部特征信息的融合,且具有优良的识别率。     

鲁棒可预测判别字典学习人脸识别方法

提出一种可预测判别K-SVD网络模型(DKSVDN)并用于人脸识别问题。该模型构造了一种新颖的字典结构,包含类别标签字典和描述字典,以兼顾判别和重构性能。相应的稀疏编码向量由标签编码向量和描述编码向量组成。针对样本稀疏编码时间效率低的问题,利用预测神经网络与判别字典学习模型协同训练的方法来加速预测稀疏编码。此外,针对DKSVDN还特别引入一种拟梦境的训练方法用于提升模型在训练集多样性不足时的鲁棒性。通过在主流人脸数据集上的对比实验证明了该模型的优良性能。     

Robust template matching with angle location using dynamic feature pairs updating

This work proposes a novel method for template matching in the wild. Different from the previous methods to search the matching position, our method obtains further ability on the angle location by dynamically updating corresponding feature pairs and rigid transformation parameters, which result in mutual enhancement of both feature extraction and template location. We propose a robust objective function with a valid feature selection for template matching against to noise disturbance, background changing, object deformation and partial occlusion. A hierarchical search strategy is used by adjusting the size of feature patch to improve the matching effectiveness. In addition, we extend the proposed method to match image sequences. It is beneficial to propagate reasonable feature pairs to a sequential object as initialization, recalling a stable tracking result. Extensive experiments are tested on the public database with challenging images and sequences. Experimental results demonstrate the merits of the proposed method compared to some state-of-the-art matching methods.     

多任务学习及卷积神经网络在人脸识别中的应用

随着深度学习的发展,近年来人脸识别借助深度学习技术取得了巨大突破。但是在已有的基于深度学习的人脸识别框架中,各个任务（人脸鉴别、认证和属性分类等）都是相互独立设计、运作的,使得整体算法低效、耗时。针对这些问题,提出一种基于多任务框架的深度卷积网络。通过将人脸鉴别、认证和属性分类同时作为网络目标函数,端到端地训练整个深度卷积网络,算法简洁高效。此网络可以同时完成上述三个任务,不需要额外的步骤。实验结果显示,即使在有限的数据支持下,该方法依然能够取得不错的性能,在人脸识别权威数据集LFW上获得了97.3%的精度。     

Score optimization and template updating in a biometric technique for authentication in mobiles based on gestures

This article focuses on the evaluation of a biometric technique based on the performance of an identifying gesture by holding a telephone with an embedded accelerometer in his/her hand. The acceleration signals obtained when users perform gestures are analyzed following a mathematical method based on global sequence alignment. In this article, eight different scores are proposed and evaluated in order to quantify the differences between gestures, obtaining an optimal EER result of 3.42% when analyzing a random set of 40 users of a database made up of 80 users with real attempts of falsification. Moreover, a temporal study of the technique is presented leeding to the need to update the template to adapt the manner in which users modify how they perform their identifying gesture over time. Six updating schemes have been assessed within a database of 22 users repeating their identifying gesture in 20 sessions over 4 months, concluding that the more often the template is updated the better and more stable performance the technique presents.     

Regularized locality preserving discriminant analysis for face recognition

This paper proposes a regularized locality preserving discriminant analysis (RLPDA) approach for facial feature extraction and recognition. The RLPDA approach decomposes the eigenspace of the locality preserving within-class scatter matrix into three subspaces, i.e., the face space, the noise space and the null space, and then regularizes the three subspaces differently according to their predicted eigenvalues. As a result, the proposed approach integrates discriminative information in all of the three subspaces, de-emphasizes the effect of the eigenvectors corresponding to the small eigenvalues, and meanwhile suppresses the small sample size problem. Extensive experiments on ORL face database, FERET face subset and UMIST face database illustrate the effectiveness of the proposed approach.     

子模式局部保持映射人脸识别

研究表明基于整体思想的人脸识别方法由于忽略图像的局部信息,在识别性能方面不如局部信息特征保持较好的基于子模块思想的识别算法。基于应用流形技术对图像降维后能够较好保持非线性子流形中的局部数据流形结构,提出了一种改进的子模式局部保持映射人脸识别算法。其主要思想是将同类的不同图像一并划分子集,由同位置子图组成子模块,并对子模块运用LPP算法学习其流形结构,与将不同类图像一并划分子集学习流形的方法不同。实验表明,该算法能更好地保持人脸图像的局部流形结构和信息特征,提高了识别率。     

基于S-LISSOM模型的人脸识别方法

提出了一种利用视皮层认知模型识别人脸的方法。该方法建立一种简化的感受野切片连接自组织映射简化模型(S LISSOM),模拟人脸图像在大脑视皮层的映射特征,作为隐马尔可夫模型(HMM)的观测向量进行人脸识别。实验结果同其他特征的人脸识别方法进行了比较,该方法更加有效的提取的人脸特征,提高了人脸识别率。