基于人脸认知模式的相似脸搜索

目的 人类对人脸认知模式的探索由来已久,并且已经成功应用于美容整形等研究领域。然而,目前在计算机视觉和模式识别领域,计算人脸相似度的方法没有考虑人对人脸的认知模式,使得现有方法的计算结果从人的认知习惯角度来讲并非最佳。为克服以上缺陷,提出一种基于人脸认知模式的相似脸搜索算法。方法 依据人脸认知模式,选取特征点,并计算特征量,构造各面部器官（眼睛、鼻子、嘴巴、脸型）分类模型,即面部器官形状相似性度量模型,并采用圆形LBP算子,计算两幅人脸对应器官的纹理相似度,二者综合作为相似脸搜索的依据。结果 分别用本文方法和代表相似脸搜索最高水平的Face++的方法对80幅正面、中性表情、平视角度拍摄的人脸图像进行测试。本文方法的整体准确率高于Face++方法,其中,TOP1、TOP2最相似搜索结果准确率优势明显,均高出Face++方法12%以上。结论 实验结果表明,本文方法的搜索结果更加符合人脸认知模式,可应用于正面、中性表情、平视角度拍摄的人脸图像的相似脸搜索。此外,还可以将此类基于认知模式的图像搜索思路推广应用于商业领域,如基于图像的相似网购商品搜索等。     

Video-to-video face authentication system robust to pose variations

High-quality still-to-still (image-to-image) face authentication has shown success under controlled conditions in many safety applications. However, video-to-video face authentication is still challenging due to appearance variations caused by pose changes. In this paper, we propose a video-to-video face authentication system that is robust to pose variations by making use of synthesized frontal face appearance that contains both texture and shape information. To obtain the appearance, we first reconstruct 3D face shape from face feature points detected from the video using active shape model (ASM). Conventional ASM algorithms cannot handle large pose variations and fast head movement exhibited in video sequences. To address these problems, we present a novel prediction-assisted approach that is capable of providing an accurate shape initiation as well as automatically switching on multi-view models for ASM. Then we can generate frontal shape mesh from the reconstructed 3D face shape. Based on the mesh, we synthesize frontal face appearance with the ASM-detected faces in video. For authentication, in order to match the synthesized appearances of enrollment and probe, we propose a 2-directional 2-dimensional client specific fisher’s linear discriminant algorithm. The proposed algorithm is a variant of fisher’s linear discriminant (FLD) and directly computes eigenvectors of image scatter matrices in row and column direction without matrix-to-vector conversion. In experiments, our authentication system is compared with the other state-of-art approaches on public face database and our face database. The results show that our system demonstrates a higher authentication accuracy and pose-robust performance.     

Elastic shape-texture matching for human face recognition

In this paper, a novel, elastic, shape-texture matching method, namely ESTM, for human face recognition is proposed. In our approach, both the shape and the texture information are used to compare two faces without establishing any precise pixel-wise correspondence. The edge map is used to represent the shape of an image, while the texture information is characterized by both the Gabor representations and the gradient direction of each pixel. Combining these features, a shape-texture Hausdorff distance is devised to compute the similarity of two face images. The elastic matching is robust to small, local distortions of the feature points such as those caused by facial expression variations. In addition, the use of the edge map, Gabor representations and the direction of the image gradient can all alleviate the effect of illumination to a certain extent.With different databases, experimental results show that our algorithm can always achieve a better performance than other face recognition algorithms under different conditions, except when an image is under poor and uneven illumination. Experiments based on the Yale database, AR database, ORL database and YaleB database show that our proposed method can achieve recognition rates of 88.7%, 97.7%, 78.3% and 89.5%, respectively.     

Using Stereo Matching with General Epipolar Geometry for 2D Face Recognition across Pose

Face recognition across pose is a problem of fundamental importance in computer vision. We propose to address this problem by using stereo matching to judge the similarity of two, 2D images of faces seen from different poses. Stereo matching allows for arbitrary, physically valid, continuous correspondences. We show that the stereo matching cost provides a very robust measure of similarity of faces that is insensitive to pose variations. To enable this, we show that, for conditions common in face recognition, the epipolar geometry of face images can be computed using either four or three feature points. We also provide a straightforward adaptation of a stereo matching algorithm to compute the similarity between faces. The proposed approach has been tested on the CMU PIE data set and demonstrates superior performance compared to existing methods in the presence of pose variation. It also shows robustness to lighting variation.     

Face Matching in Large Database by Self-Organizing Maps

A novel self-organizing map (SOM) based retrieval system is proposed for performing face matching in large database. The proposed system provides a small subset of faces that are most similar to a given query face, from which user can easily verify the matched images. The architecture of the proposed system consists of two major parts. First, the system provides a generalized integration of multiple feature-sets using multiple self-organizing maps. Multiple feature-sets are obtained from different feature extraction methods like Gabor filter, Local Autocorrelation Coefficients, etc. In this platform, multiple facial features are integrated to form a compressed feature vector without concerning scaling and length of individual feature set. Second, an SOM is trained to organize all the face images in a database through using the compressed feature vector. Using the organized map, similar faces to a query can be efficiently identified. Furthermore, the system includes a relevance feedback to enhance the face retrieval performance. The proposed method is computationally efficient. Comparative results show that the proposed approach is promising for identifying face in a given large image database.     

Ranking,clustering and fusing the normalized LBP temporal facial features for face recognition in video sequences

This paper proposes a novel approach for recognizing faces in videos with high recognition rate. Initially, the feature vector based on Normalized Local Binary Patterns is obtained for the face region. A set of training and testing videos are used in this face recognition procedure. Each frame in the query video is matched with the signature of the faces in the database using Euclidean distance and a rank list is formed. Each ranked list is clustered and its reliability is analyzed for re-ranking. Multiple re-ranked lists of the query video is fused together to form a video signature. This video signature embeds diverse intra-personal variations such as poses, expressions and facilitates in matching two videos with large variations. For matching two videos, their composite ranked lists are compared using a Kendall Tau distance measure. The developed methods are deployed on the YouTube and ChokePoint videos, and they exhibit significant performance improvement owing to their novel approach when compared with the existing techniques.

     

Robust facial feature tracking under varying face pose and facial expression

This paper presents a hierarchical multi-state pose-dependent approach for facial feature detection and tracking under varying facial expression and face pose. For effective and efficient representation of feature points, a hybrid representation that integrates Gabor wavelets and gray-level profiles is proposed. To model the spatial relations among feature points, a hierarchical statistical face shape model is proposed to characterize both the global shape of human face and the local structural details of each facial component. Furthermore, multi-state local shape models are introduced to deal with shape variations of some facial components under different facial expressions. During detection and tracking, both facial component states and feature point positions, constrained by the hierarchical face shape model, are dynamically estimated using a switching hypothesized measurements (SHM) model. Experimental results demonstrate that the proposed method accurately and robustly tracks facial features in real time under different facial expressions and face poses.     

Human face recognition using fuzzy multilayer perceptron

In this work a novel method for human face recognition that is based on fuzzy neural network has been presented. Here, Gabor wavelet transformation is used for extraction of features from face images as it deals with images in spatial as well as in frequency domain to capture different local orientations and scales efficiently. In face recognition problem multilayer perceptron (MLP) has already been adopted owing to its efficiency, but it does not capture overlapping and nonlinear manifolds of faces which exhibit different variations in illumination, expression, pose, etc. A fuzzy MLP on the other hand performs better than an MLP because fuzzy MLP can identify decision surfaces in case of nonlinear overlapping classes, whereas an MLP is restricted to crisp boundaries only. In the present work, a new approach for fuzzification of the feature sets obtained through Gabor wavelet transforms has been discussed. The feature vectors thus obtained are classified using a newly designed fuzzified MLP. The system has been tested on a composite database (DB-C) consisting of the ORL face database and another face database created for this purpose and a recognition rate of 97.875% with fuzzy MLP against a recognition rate of only 81.25% with MLP whose feature vectors were also obtained through same Gabor wavelet transforms has been obtained.     

Multi-view based face chin contour extraction

Chin contour is an important facial feature to build a 3D morphable model, the core step of which is to establish feature points correspondence between each face in the training set and the reference face. In this paper, robust face detection is implemented firstly using probabilistic method. A probability of detection is obtained for each image of different position and at several scales and poses. Then, the chin contours are extracted accurately using the active shape model (ASM), which depends on the parameters obtained from the face detection. From frontal (0°) to profile (90°) faces that are equally divided into 10 parts, we train 10 flexible models. Then, different flexible models are used to extract the face chin contour according to the corresponding face pose. Experimental results show that the proposed approach can extract the chin contours of different people across different poses with good accuracy.     

Face recognition using the nearest feature line method

We propose a classification method, called the nearest feature line (NFL), for face recognition. Any two feature points of the same class (person) are generalized by the feature line (FL) passing through the two points. The derived FL can capture more variations of face images than the original points and thus expands the capacity of the available database. The classification is based on the nearest distance from the query feature point to each FL. With a combined face database, the NFL error rate is about 43.7-65.4% of that of the standard eigenface method. Moreover, the NFL achieves the lowest error rate reported to date for the ORL face database.     

Tied factors analysis for high-dimensional image feature extraction and recognition application

Feature extraction from images, which are typical of high dimensionality, is crucial to the recognition performance. To explore the discriminative information while depressing the intra-class variations due to variable illumination and view conditions, we propose a factor analysis framework for separate “content” from “style,” identifying a familiar face seen under unfamiliar viewing conditions, classifying familiar poses presented in an unfamiliar face, estimating age across unfamiliar faces. The framework applies efficient algorithms derived from objective factor separating functions and space mapping functions, which can produce sufficiently expressive representations of feature extraction and dimensionality reduction. We report promising results on three different tasks in the high-dimensional image perceptual domains: face identification with two benchmark face databases, facial pose classification with a benchmark facial pose database, extrapolation of age to unseen facial image. Experimental results show that our approach produced higher classification performance when compared to classical LDA, WLDA, LPP, MFA, and DLA algorithms.     

一种鲁棒的人脸特征定位方法

提出了一种基于AdaBoost算法和C-V方法的人脸特征定位方法。首先根据AdaBoost算法训练样本得到脸、眼、鼻、嘴4个检测器;然后结合人脸边缘图像的先验规则,使用人脸检测器提取人脸区域;接着利用眼、鼻、嘴检测器从人脸区域中检测出人脸特征所在的矩形区域;最后利用C-V方法从各个特征区域中分割出人脸特征的轮廓,进而得到人脸关键特征点的位置。在DTU IMM人脸测试集上,眼睛的检测率为100%,鼻子的检测率为95.3%,嘴巴的检测率为98.4%,提取出的特征点位置准确。实验结果表明方法是有效和鲁棒的。     

基于少量特征点的多模态人脸识别

针对二维人脸识别对姿态和光照变化较为敏感的问题,提出了一种基于少量特征点的多模态人脸识别方法。在训练阶段,对三维人脸数据进行二次处理和数据挖掘,为建立完备的特征模板奠定了基础;提出了一种简洁高效的样本聚类方法,克服了特征提取过程中的非线性问题;通过局部特征分析(Local Feature Analysis,LFA)实现了特征点"局部"与"全局"信息的融合。实验证明该方法在具有较高执行效率的同时,对人脸图像的姿态和光照变化具有理想的鲁棒性,在WHU-3D小规模人脸数据库上取得了98.06%的识别率。     

基于遗传算法重采样的人脸样本扩张

无论是对人脸检测还是人脸识别来说,训练或测试一个分类器都要进行数据的收集,目前所有基于统计学习的方法都存在这个问题.提出了一种针对已有的人脸样本通过采用遗传算法进行重采样来扩张样本的算法.其基本思想是,基于人脸样本由有限的部件构成,而且遗传算法可以用于模拟自然界中的遗传过程.这种模拟可以涵盖人脸的一些变化,比如不同的光照、姿态、饰物、图片质量等.为了证明该算法所生成样本的推广能力,将这些生成的样本用于训练一个基于AdaBoost的人脸检测器,并且将它在MIT+CMU的正面人脸测试库上进行了测试.实验结果表明,通过这种方法来收集数据可以有效地提高数据收集的速度和效率.     

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.     

可变光照条件下的人脸识别

主要解决人脸识别中因光照变化导致误识或者拒识的问题。使用DOG（高斯差分变换）对原始人脸图像样本集（A）进行处理,将滤波后的人脸图像样本集（B）加入到原始样本集（A）中,采用了新的方法将样本集A和B进行融合,则既对极端光照条件下人脸图像进行了矫正,又不影响正常光照条件下的人脸识别。在分类阶段,引入了SRC（Sparse Representation Classification）分类器代替传统分类器,提升了在低错误接收率下的识别率,改善因光照剧烈变换而导致的无法识别或者误识的情况。在公开人脸库Yale-B、CMU-PIE以及ORL上的实验结果表明,该方法在不同光照条件下可以提高识别率,改善拒识和误识情况。     

EM enhancement of 3D head pose estimated by point at infinity

Head pose estimation is a key task for visual surveillance, HCI and face recognition applications. In this paper, a new approach is proposed for estimating 3D head pose from a monocular image. The approach assumes the full perspective projection camera model. Our approach employs general prior knowledge of face structure and the corresponding geometrical constraints provided by the location of a certain vanishing point to determine the pose of human faces. To achieve this, eye-lines, formed from the far and near eye corners, and mouth-line of the mouth corners are assumed parallel in 3D space. Then the vanishing point of these parallel lines found by the intersection of the eye-line and mouth-line in the image can be used to infer the 3D orientation and location of the human face. In order to deal with the variance of the facial model parameters, e.g. ratio between the eye-line and the mouth-line, an EM framework is applied to update the parameters. We first compute the 3D pose using some initially learnt parameters (such as ratio and length) and then adapt the parameters statistically for individual persons and their facial expressions by minimizing the residual errors between the projection of the model features points and the actual features on the image. In doing so, we assume every facial feature point can be associated to each of features points in 3D model with some a posteriori probability. The expectation step of the EM algorithm provides an iterative framework for computing the a posterori probabilities using Gaussian mixtures defined over the parameters. The robustness analysis of the algorithm on synthetic data and some real images with known ground-truth are included.     

An efficient approach for face recognition based on common eigenvalues

In this paper, a simple technique is proposed for face recognition among many human faces. It is based on the polynomial coefficients, covariance matrix and algorithm on common eigenvalues. The main advantage of the proposed approach is that the identification of similarity between human faces is carried out without computing actual eigenvalues and eigenvectors. A symmetric matrix is calculated using the polynomial coefficients-based companion matrices of two compared images. The nullity of a calculated symmetric matrix is used as similarity measure for face recognition. The value of nullity is very small for dissimilar images and distinctly large for similar face images. The feasibility of the propose approach is demonstrated on three face databases, i.e., the ORL database, the Yale database B and the FERET database. Experimental results have shown the effectiveness of the proposed approach for feature extraction and classification of the face images having large variation in pose and illumination.     

三维脸部网格模型的交互式调整

脸部网络模型的建立是基于模型的人脸合成技术的关键步骤。提出了一种结合自动和交互方式，利用正交图象的三维人脸模型调整算法，首先利用区域增长法和矩形模板匹配确定正面图象中人脸及各特征区域的位置，利用变形模板自动提取人脸完整特征；然后交互地修正人脸特点的准确正面位置，并从侧面图象提取特征点的深度；最后算法自动确定脸部姿态和利用反向距离内插调整模型非特征点，获得输和人脸模型。实验结果表明，该算法简便实用，费时较少，具有一定的实用价值。     

刚性区域特征点的3维人脸识别

目的 针对3维人脸识别中存在表情变化的问题,提出了一种基于刚性区域特征点的3维人脸识别方法。方法 该方法首先在人脸纹理图像上提取人脸图像的特征点,并删除非刚性区域内的特征点,然后根据采样点的序号,在人脸空间几何信息上得到人脸图像特征点的3维几何信息,并建立以特征点为中心的刚性区域内的子区域,最后以子区域为局部特征进行人脸识别测试,得到不同子区域对人脸识别的贡献,并以此作为依据对人脸识别的结果进行加权统计。结果 在FRGC v2.0的3维人脸数据库上进行实验测试,该方法的识别准确率为98.5%,当错误接受率（FAR）为0.001时的验证率为99.2%,结果表明,该方法对非中性表情下的3维人脸识别具有很好的准确性。结论 该方法可以有效克服表情变化对3维人脸识别的影响,同时对3维数据中存在的空洞和尖锐噪声等因素具有较好的鲁棒性,对提高3维人脸识别性能具有重要意义。