3D Face Recognition Using Simulated Annealing and the Surface Interpenetration Measure

This paper presents a novel automatic framework to perform 3D face recognition. The proposed method uses a Simulated Annealing-based approach (SA) for range image registration with the Surface Interpenetration Measure (SIM), as similarity measure, in order to match two face images. The authentication score is obtained by combining the SIM values corresponding to the matching of four different face regions: circular and elliptical areas around the nose, forehead, and the entire face region. Then, a modified SA approach is proposed taking advantage of invariant face regions to better handle facial expressions. Comprehensive experiments were performed on the FRGC v2 database, the largest available database of 3D face images composed of 4,007 images with different facial expressions. The experiments simulated both verification and identification systems and the results compared to those reported by state-of-the-art works. By using all of the images in the database, a verification rate of 96.5 percent was achieved at a False Acceptance Rate (FAR) of 0.1 percent. In the identification scenario, a rank-one accuracy of 98.4 percent was achieved. To the best of our knowledge, this is the highest rank-one score ever achieved for the FRGC v2 database when compared to results published in the literature.     

Fast and Accurate 3D Face Recognition

In this paper we present a new robust approach for 3D face registration to an intrinsic coordinate system of the face. The intrinsic coordinate system is defined by the vertical symmetry plane through the nose, the tip of the nose and the slope of the bridge of the nose. In addition, we propose a 3D face classifier based on the fusion of many dependent region classifiers for overlapping face regions. The region classifiers use PCA-LDA for feature extraction and the likelihood ratio as a matching score. Fusion is realised using straightforward majority voting for the identification scenario. For verification, a voting approach is used as well and the decision is defined by comparing the number of votes to a threshold. Using the proposed registration method combined with a classifier consisting of 60 fused region classifiers we obtain a 99.0% identification rate on the all vs first identification test of the FRGC v2 data. A verification rate of 94.6% at FAR=0.1% was obtained for the all vs all verification test on the FRGC v2 data using fusion of 120 region classifiers. The first is the highest reported performance and the second is in the top-5 of best performing systems on these tests. In addition, our approach is much faster than other methods, taking only 2.5 seconds per image for registration and less than 0.1 ms per comparison. Because we apply feature extraction using PCA and LDA, the resulting template size is also very small: 6 kB for 60 region classifiers.     

基于三维矫正和相似性学习的无约束人脸验证

针对无约束条件下的人脸图像样本少、面部姿态变化大、被遮挡以及背景复杂等问题,提出一种结合三维人脸矫正与相似性学习相结合的人脸验证算法（sub-SL）。首先,通过三维人脸矫正方法对人脸图像进行姿态矫正,将图像中的人脸矫正为标准正面脸;其次,裁剪该正面脸的脸部相关区域,去除复杂的图像背景;最后,利用基于个体子空间的相似性学习方法对图像对之间的相似度进行度量,完成人脸验证。实验采用了几个以LFW（Labeled Faces in the Wild）数据库为基础的经过预处理操作（例如人脸矫正、裁剪等）后建立起来的数据库。在基于局部三值模式（LTP）的特征提取方法并且训练图像对数为625的实验中,sub-SL算法的识别率比利用马氏距离进行度量学习的算法sub-ML以及结合了马氏距离与相似性学习的度量学习算法sub-SML分别高出了15.6%和8.4%。实验结果表明,sub-SL算法能够有效提高无约束条件下人脸识别的准确率。     

结合SIFT特征的人脸验证

人脸验证是人脸识别领域的一个分支,是安防领域的研究热点。根据人脸验证的特殊性,使用尺度不变特征（SIFT）算法,并利用图像分块方法,将特征点划分为数量特征以及位置特征,达到人脸验证的目的。所需验证的一对图像配准后,使用SIFT算法寻找出匹配特征点,对待匹配的2幅图像进行分块,统计各个分块中的特征点数量,获得匹配向量。判断两幅图像的特征点数量是否达到阈值,若达到则计算两幅图像的匹配向量相似度,若相似度达到标准,则认为图像对匹配,若有任何一个条件没有满足,则认为不匹配。利用CAS和FERET数据库进行测试,虚警率达到19%,漏警率达到0.3%,验证了算法的有效性以及安全性。该算法经优化后,可用于人脸验证。     

A novel framework for automatic 3D face recognition using quality assessment

The quality of biometric samples plays an important role in biometric authentication systems because it has a direct impact on verification or identification performance. In this paper, we present a novel 3D face recognition system which performs quality assessment on input images prior to recognition. More specifically, a reject option is provided to allow the system operator to eliminate the incoming images of poor quality, e.g. failure acquisition of 3D image, exaggerated facial expressions, etc.. Furthermore, an automated approach for preprocessing is presented to reduce the number of failure cases in that stage. The experimental results show that the 3D face recognition performance is significantly improved by taking the quality of 3D facial images into account. The proposed system achieves the verification rate of 97.09% at the False Acceptance Rate (FAR) of 0.1% on the FRGC v2.0 data set.     

Horizontal and Vertical 2DPCA-Based Discriminant Analysis for Face Verification on a Large-Scale Database

This paper first discusses some theoretical properties of 2D principal component analysis (2DPCA) and then presents a horizontal and vertical 2DPCA-based discriminant analysis (HVDA) method for face verification. The HVDA method, which applies 2DPCA horizontally and vertically on the image matrices (2D arrays), achieves lower computational complexity than the traditional PCA and Fisher linear discriminant analysis (LDA)-based methods that operate on high dimensional image vectors (1D arrays). The horizontal 2DPCA is invariant to vertical image translations and vertical mirror imaging, and the vertical 2DPCA is invariant to horizontal image translations and horizontal mirror imaging. The HVDA method is therefore less sensitive to imprecise eye detection and face cropping, and can improve upon the traditional discriminant analysis methods for face verification. Experiments using the face recognition grand challenge (FRGC) and the biometric experimentation environment system show the effectiveness of the proposed method. In particular, for the most challenging FRGC version 2 Experiment 4, which contains 12thinspace776 training images, 16 028 controlled target images, and 8014 uncontrolled query images, the HVDA method using a color configuration across two color spaces, namely, the YIQ and the YCbCr color spaces, achieves the face verification rate (ROC III) of 78.24% at the false accept rate of 0.1%.     

基于数据库编程语言的海量邮件数据分类技术

针对海量邮件数据的处理需求和实际业务需要,设计了基于数据库编程语言的海量邮件自动分类系统。该系统由特征学习模块、数据库查询模块和贝叶斯分类模块3部分构成。结合贝叶斯分类算法,利用PL/SQL语言与数据库交互时的高效性特点,在ORACLE PL/SQL存储过程中完成对未知邮件的特征提取和表示,实现对海量邮件数据的有效分类。     

基于二阶双向二维主成分分析的人脸识别方法

为了克服光照变化较大的情况对识别率的影响,提出基于二阶双向二维主成分分析(Sec-(2D)2PCA)的人脸识别方法。丢弃提取人脸图像的(2D)2PCA的前几个反映光照信息的主成分。在剩余图像中再次使用(2D)2PCA方法。Yale人脸库B和Yale人脸库上的试验结果表明,该方法在识别性能上优于2DPCA、(2D)2PCA、Sec-2DPCA方法。     

Unconstrained Still/Video-Based Face Verification with Deep Convolutional Neural Networks

Over the last 5 years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements for object detection and recognition problems. This has been made possible due to the availability of large annotated datasets, a better understanding of the non-linear mapping between input images and class labels as well as the affordability of GPUs. In this paper, we present the design details of a deep learning system for unconstrained face recognition, including modules for face detection, association, alignment and face verification. The quantitative performance evaluation is conducted using the IARPA Janus Benchmark A (IJB-A), the JANUS Challenge Set 2 (JANUS CS2), and the Labeled Faces in the Wild (LFW) dataset. The IJB-A dataset includes real-world unconstrained faces of 500 subjects with significant pose and illumination variations which are much harder than the LFW and Youtube Face datasets. JANUS CS2 is the extended version of IJB-A which contains not only all the images/frames of IJB-A but also includes the original videos. Some open issues regarding DCNNs for face verification problems are then discussed.     

Downsampling sparse representation and discriminant information aided occluded face recognition

In this paper, a strategy is proposed to deal with a challenging research topic, occluded face recog- nition. Our approach relies on sparse representation on downsampled input image to first locate unoccluded face parts, and then exploits the linear discriminant ability of those pixels to identify the input subject. The advantages and novelties of our method include, 1） since the sparse representation based occlusion detection is conducted on dowsampled image, our algorithm is much faster than classic SRC; 2） the discriminant informa- tion learned from training samples is combined with sparse representation to recognize occluded face for the first time. The verification experiments are conducted on both sinmlated block occlusion images and genuine occluded images.     

Biometric recognition using 3D ear shape

Previous works have shown that the ear is a promising candidate for biometric identification. However, in prior work, the preprocessing of ear images has had manual steps and algorithms have not necessarily handled problems caused by hair and earrings. We present a complete system for ear biometrics, including automated segmentation of the ear in a profile view image and 3D shape matching for recognition. We evaluated this system with the largest experimental study to date in ear biometrics, achieving a rank-one recognition rate of 97.8 percent for an identification scenario and an equal error rate of 1.2 percent for a verification scenario on a database of 415 subjects and 1,386 total probes.     

Feature-based affine-Invariant localization of faces

We present a novel method for localizing faces in person identification scenarios. Such scenarios involve high resolution images of frontal faces. The proposed algorithm does not require color, copes well in cluttered backgrounds, and accurately localizes faces including eye centers. An extensive analysis and a performance evaluation on the XM2VTS database and on the realistic BioID and BANCA face databases is presented. We show that the algorithm has precision superior to reference methods.     

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。     

Finger texture biometric verification exploiting Multi-scale Sobel Angles Local Binary Pattern features and score-based fusion

In this paper a new feature extraction method called Multi-scale Sobel Angles Local Binary Pattern (MSALBP) is proposed for application in personal verification using biometric Finger Texture (FT) patterns. This method combines Sobel direction angles with the Multi-Scale Local Binary Pattern (MSLBP). The resulting characteristics are formed into non-overlapping blocks and statistical calculations are implemented to form a texture vector as an input to an Artificial Neural Network (ANN). A Probabilistic Neural Network (PNN) is applied as a multi-classifier to perform the verification. In addition, an innovative method for FT fusion based on individual finger contributions is suggested. This method is considered as a multi-object verification, where a finger fusion method named the Finger Contribution Fusion Neural Network (FCFNN) is employed for the five fingers. Two databases have been employed in this paper: PolyU3D2D and Spectral 460 nm (S460) from CASIA Multi-Spectral (CASIA-MS) images. The MSALBP feature extraction method has been examined and compared with different Local Binary Pattern (LBP) types; in classification it yields the lowest Equal Error Rate (EER) of 0.68% and 2% for PolyU3D2D and CASIA-MS (S460) databases, respectively. Moreover, the experimental results revealed that our proposed finger fusion method achieved superior performance for the PolyU3D2D database with an EER of 0.23% and consistent performance for the CASIA-MS (S460) database with an EER of 2%.     

PCA-based image recombination for multimodal 2D + 3D face recognition

Most of the existing approaches of multimodal 2D + 3D face recognition exploit the 2D and 3D information at the feature or score level. They do not fully benefit from the dependency between modalities. Exploiting this dependency at the early stage is more effective than the later stage. Early fusion data contains richer information about the input biometric than the compressed features or matching scores. We propose an image recombination for face recognition that explores the dependency between modalities at the image level. Facial cues from the 2D and 3D images are recombined into a more independent and discriminating data by finding transformation axes that account for the maximal amount of variances in the images. We also introduce a complete framework of multimodal 2D + 3D face recognition that utilizes the 2D and 3D facial information at the enrollment, image and score levels. Experimental results based on NTU-CSP and Bosphorus 3D face databases show that our face recognition system using image recombination outperforms other face recognition systems based on the pixel- or score-level fusion.     

结合小波变换和稀疏表征的鲁棒人脸识别

在人脸识别中,如何消除光照、表情、遮挡等不利因素的影响,提高识别的鲁棒性是当前急需解决的热点研究问题。本文提出了一种基于小波变换和稀疏表征的鲁棒人脸识别方法,首先对人脸图像进行小波变换,将变换得到的4个子带LL、LH、HL、HH作为基函数构成字典;然后将测试图像的LL子带在字典上稀疏分解;最后依据重构残差最小原则进行分类识别。在Yale人脸库上的实验结果表明该方法性能优于对比方法。     

Illumination normalization of facial images by reversing the process of image formation

Variations in illumination degrade the performance of appearance based face recognition. We present a novel algorithm for the normalization of color facial images using a single image and its co-registered 3D pointcloud (3D image). The algorithm borrows the physically based Phong’s lighting model from computer graphics which is used for rendering computer images and employs it in a reverse mode for the calculation of face albedo from real facial images. Our algorithm estimates the number of the dominant light sources and their directions from the specularities in the facial image and the corresponding 3D points. The intensities of the light sources and the parameters of the Phong’s model are estimated by fitting the Phong’s model onto the facial skin data. Unlike existing approaches, our algorithm takes into account both Lambertian and specular reflections as well as attached and cast shadows. Moreover, our algorithm is invariant to facial pose and expression and can effectively handle the case of multiple extended light sources. The algorithm was tested on the challenging FRGC v2.0 data and satisfactory results were achieved. The mean fitting error was 6.3% of the maximum color value. Performing face recognition using the normalized images increased both identification and verification rates.