一种用于脸部特征检测的分层概率模型研究

脸部特征检测问题是计算机视觉领域的研究热点。因为脸部外观和形态随着条件的变化而变化,因此面部特征检测比较复杂。针对现有脸部特征检测算法的不足,提出一种已知图像测量数据后能够推断出真实脸部特征位置的分层概率模型。针对每个脸部子部位的局部形态变化进行间接建模;通过搜索模型的最优结构和参数设置,在更高层次上学习脸部子部位、脸部表情和姿态间的联合关系。该模型综合利用了脸部子部位自下而上的形态约束以及脸部子部位间自上而下的关系约束来推断出脸部特征的真实位置。利用基准数据库进行了仿真实验。实验结果表明,该方法的检测性能要明显优于目前最新的人脸特征检测算法。     

基于多状态分层模型的有表情人脸配准

将人脸表情变化范围离散化表示为多状态部件模型,以便描述人脸非线性变化。引入多方向局部梯度信息,建立反投影概率图来改善原始灰度图像的外观模式表达,基于级联的卷积神经网络实现渐进分层的人脸配准。根据整脸和不同区域的图像实现人脸形状初始化,并判断当前部件状态。根据正确状态的人脸模型回归人脸形状参数,完成最终的精细配准。与其他几种常用算法在数据库上进行了定量比较,结果表明该算法改善了表情变化剧烈时人脸配准的效果,在计算量相当的情况下,正确率和处理速度等方面都达到很好的性能,具有明显的实用价值。     

A robust incremental clustering-based facial feature tracking

Emerging significance of person-independent, emotion specific facial feature tracking has been actively tracked in the machine vision society for decades. Among distinct methods, the Constrained Local Model (CLM) has shown significant results in person-independent feature tracking. In this paper, we propose an automatic, efficient, and robust method for emotion specific facial feature detection and tracking from image sequences. A novel tracking system along with 17-point feature model on the frontal face region has also been proposed to facilitate the tracking of human basic facial expressions. The proposed feature tracking system keeps patch images and face shapes till certain number of key frames incorporating CLM-based tracker. After that, incremental patch and shape clustering algorithms is applied to build appearance model and structure model of similar patches and similar shapes respectively. The clusters in each model are built and updated incrementally and online, controlled by amount of facial muscle movement. The overall performance of the proposed Robust Incremental Clustering-based Facial Feature Tracking (RICFFT) is evaluated on the FGnet database and the Extended Cohn-Kanade (CK+) database. RICFFT demonstrates mean tracking accuracy of 97.45% and 96.64% for FGnet and CK+ database respectively. Also, RICFFT is more robust by minimizing average shape distortion error of 0.20% and 1.86% for FGnet and CK+ (apex frame) database, as compared with classic method CLM.     

Bayesian shape model for facial feature extraction and recognition

A facial feature extraction algorithm using the Bayesian shape model (BSM) is proposed in this paper. A full-face model consisting of the contour points and the control points is designed to describe the face patch, using which the warping/normalization of the extracted face patch can be performed efficiently. First, the BSM is utilized to match and extract the contour points of a face. In BSM, the prototype of the face contour can be adjusted adaptively according to its prior distribution. Moreover, an affine invariant internal energy term is introduced to describe the local shape deformations between the prototype contour in the shape domain and the deformable contour in the image domain. Thus, both global and local shape deformations can be tolerated. Then, the control points are estimated from the matching result of the contour points based on the statistics of the full-face model. Finally, the face patch is extracted and normalized using the piece-wise affine triangle warping algorithm. Experimental results based on real facial feature extraction demonstrate that the proposed BSM facial feature extraction algorithm is more accurate and effective as compared to that of the active shape model (ASM).     

多视角约束级联回归的视频人脸特征点跟踪

近年来,静态图像中人脸特征点检测算法得到了极大的改进,然而,由于真实视频中头部姿态、遮挡和光照等因素的变化,人脸特征点检测和跟踪仍然具有挑战性。为了解决这一问题,提出一种多视角约束级联回归的视频人脸特征点跟踪算法。首先,利用三维和二维稀疏点集建立变换关系,并估计初始形状;其次,由于人脸图像存在较大的姿态差异,使用仿射变换对人脸图像进行姿态矫正;在构造形状回归模型时,采用多视角约束级联回归模型减小形状方差,从而使学习到的回归模型对形状方差具有更强的鲁棒性;最后,采用重新初始化机制,并在特征点正确定位时使用归一化互相关（NCC）模板匹配跟踪算法建立连续帧之间的形状关系。在公共数据集上的实验结果表明：该算法的平均误差小于眼间距离的10%。     

局部特征脸型分类方法

本文针对传统脸型分类算法特征点定位不准和过度依赖轮廓曲线的问题,提出了一种人脸轮廓圆形邻域局部特征表达方式和脸型分类模型。首先,初步定位脸型轮廓特征点;然后,在特征点周围选取三重八连通圆形邻域,通过计算一级邻域、拓展邻域与中心区域间的纹理变化,生成二进制编码序列,构造脸型局部特征向量;最后,设计OVO-RBF-SVM多分类模型,实现脸型分类。本文方法在CAS-PEAL人脸库上进行脸型类型判别,获得了94.28%的准确率;在相同情况下,分别与基于主动形状模型和基于下颌曲线模型的脸型类型判别方法进行对比,准确率分别提高了6.64%和6.58%。本文所研究的方法在一定程度上解决了特征点定位相对不准确导致误差增加的问题,同时尽可能多利用图片原始信息,保证轮廓特征提取的准确率,具有较强的鲁棒性。通过实验证明本文方法适用于脸型分类。     

Differential optical flow applied to automatic facial expression recognition

This work compares systematically two optical flow-based facial expression recognition methods. The first one is featural and selects a reduced set of highly discriminant facial points while the second one is holistic and uses much more points that are uniformly distributed on the central face region. Both approaches are referred as feature point tracking and holistic face dense flow tracking, respectively. They compute the displacements of different sets of points along the sequence of frames describing each facial expression (i.e. from neutral to apex). First, we evaluate our algorithms on the Cohn-Kanade database for the six prototypic expressions under two different spatial frame resolutions (original and 40%-reduced). Later, our methods were also tested on the MMI database which presents higher variabilities than the Cohn-Kanade one. The results on the first database show that dense flow tracking method at original resolution slightly outperformed, in average, the recognition rates of feature point tracking method (95.45% against 92.42%) but it requires 68.24% more time to track the points. For the patterns of MMI database, using dense flow tracking at the original resolution, we achieved very similar average success rates.     

基于统计模型与Gabor小波的人脸对齐

将基于Gabor小波的人脸特征点跟踪算法与基于统计模型的主动外观模型AAM人脸特征点定位方法结合起来,实现视频中人脸的自动对齐。先利用Gabor小波进行特征点跟踪,其结果作为AAM的初始形状。利用AAM的全局形状和纹理信息作为约束,对Gabor小波的局部跟踪错误进行校正。实验表明,该方法是有效的。     

Active and dynamic information fusion for facial expression understanding from image sequences

This paper explores the use of multisensory information fusion technique with dynamic Bayesian networks (DBN) for modeling and understanding the temporal behaviors of facial expressions in image sequences. Our facial feature detection and tracking based on active IR illumination provides reliable visual information under variable lighting and head motion. Our approach to facial expression recognition lies in the proposed dynamic and probabilistic framework based on combining DBN with Ekman's facial action coding system (FACS) for systematically modeling the dynamic and stochastic behaviors of spontaneous facial expressions. The framework not only provides a coherent and unified hierarchical probabilistic framework to represent spatial and temporal information related to facial expressions, but also allows us to actively select the most informative visual cues from the available information sources to minimize the ambiguity in recognition. The recognition of facial expressions is accomplished by fusing not only from the current visual observations, but also from the previous visual evidences. Consequently, the recognition becomes more robust and accurate through explicitly modeling temporal behavior of facial expression. In this paper, we present the theoretical foundation underlying the proposed probabilistic and dynamic framework for facial expression modeling and understanding. Experimental results demonstrate that our approach can accurately and robustly recognize spontaneous facial expressions from an image sequence under different conditions.     

Incremental Clustering-Based Facial Feature Tracking Using Bayesian ART

Person-independent, emotion specific facial feature tracking have been of interest in the machine vision society for decades. Among various methods, the constrained local model (CLM) has shown significant results in person-independent feature tracking. In 63this paper, we propose an automatic, efficient, and robust method for emotion specific facial feature detection and tracking from image sequences. Considering a 17-point feature model on the frontal face region, the proposed tracking framework incorporates CLM with two incremental clustering algorithms to increase robustness and minimize tracking error during feature tracking. The Patch Clustering algorithm is applied to build an appearance model of face frames by organizing previously encountered similar patches into clusters while the shape Clustering algorithm is applied to build a structure model of face shapes by organizing previously encountered similar shapes into clusters followed by Bayesian adaptive resonance theory (ART). Both models are used to explore the similar features/shapes in the successive images. The clusters in each model are built and updated incrementally and online, controlled by amount of facial muscle movement. The overall performance of the proposed incremental clustering-based facial feature tracking (ICFFT) is evaluated using the FGnet database and the extended Cohn-Kanade (CK+) database. ICFFT demonstrates better results than baseline-method CLM and provides robust tracking as well as improved localization accuracy of emotion specific facial features tracking.     

Classifying facial actions

The facial action coding system (FAGS) is an objective method for quantifying facial movement in terms of component actions. This paper explores and compares techniques for automatically recognizing facial actions in sequences of images. These techniques include: analysis of facial motion through estimation of optical flow; holistic spatial analysis, such as principal component analysis, independent component analysis, local feature analysis, and linear discriminant analysis; and methods based on the outputs of local filters, such as Gabor wavelet representations and local principal components. Performance of these systems is compared to naive and expert human subjects. Best performances were obtained using the Gabor wavelet representation and the independent component representation, both of which achieved 96 percent accuracy for classifying 12 facial actions of the upper and lower face. The results provide converging evidence for the importance of using local filters, high spatial frequencies, and statistical independence for classifying facial actions     

一种特征加权融合人脸识别方法

针对传统人脸识别算法在非限制条件下识别准确率不高的问题,提出了一种特征加权融合人脸识别方法(DLWF⁺)。根据人脸面部左眼、右眼、鼻子、嘴、下巴等5个器官位置,将人脸图像划分成5个局部采样区域;将得到的5个局部采样区域和整幅人脸图像分别输入到对应的神经网络中进行网络权值调整,完成子网络的构建;利用softmax回归求出6个相似度向量并组成相似度矩阵与权向量相乘得出最终的识别结果。经ORL和WFL人脸库上进行实验验证,识别准确率分别达到97%和91.63%。实验结果表明:该算法能够有效提高人脸识别能力,与传统识别算法相比在限制条件和非限制条件下都具有较高的识别准确率。     

基于局部融合特征与分层增量树的快速人脸识别算法

传统的人脸识别模型采用离线方式进行训练,同时由于人脸特征维数较高导致算法的实时性不足。文中分别从人脸特征与分类器两方面来构建快速的人脸识别算法。首先使用 SDM(Supervised Descent Method)算法进行人脸特征点定位,提取每个人脸特征点邻域内的局部(Multi Block-Center Symmetric Local Binary Patterns,MB-CSLBP)特征,并将所有的人脸特征点邻域特征以串联的方式构成局部融合特征,即所提出的局部融合MB-CSLBP特征LFP-MB-CSLBP(Local Fusion Feature of MB-CSLBP)。将以上特征送入分层增量树HI-tree(Hierarchical Incremental tree)中进行人脸识别模型的在线训练。分层增量树是使用分层聚类算法来实现增量式学习的,因此其能够以在线的方式对识别模型进行训练,具有较高的实时性与准确性。最后在3种不同的人脸库以及摄像头采集的人脸视频上对算法的识别率与实时性进行测试。实验结果表明,相比于当前其他算法,所提算法具有较高的人脸识别率与实时性。     

基于特征点表情变化的3维人脸识别

目的 为克服表情变化对3维人脸识别的影响,提出一种基于特征点提取局部区域特征的3维人脸识别方法。方法 首先,在深度图上应用2维图像的ASM(active shape model)算法粗略定位出人脸特征点,再根据Shape index特征在人脸点云上精确定位出特征点。其次,提取以鼻中为中心的一系列等测地轮廓线来表征人脸形状;然后,提取具有姿态不变性的Procrustean向量特征(距离和角度)作为识别特征;最后,对各条等测地轮廓线特征的分类结果进行了比较,并对分类结果进行决策级融合。结果 在FRGC V2.0人脸数据库分别进行特征点定位实验和识别实验,平均定位误差小于2.36 mm,Rank-1识别率为98.35%。结论 基于特征点的3维人脸识别方法,通过特征点在人脸近似刚性区域提取特征,有效避免了受表情影响较大的嘴部区域。实验证明该方法具有较高的识别精度,同时对姿态、表情变化具有一定的鲁棒性。     

深度学习人脸特征点自动定位综述

人脸特征点定位是根据输入的人脸数据自动定位出预先按人脸生理特征定义的眼角、鼻尖、嘴角和脸部轮廓等面部关键特征点,在人脸识别和分析等系统中起着至关重要的作用。本文对基于深度学习的人脸特征点自动定位进行综述,阐释了人脸特征点自动定位的含义,归纳了目前常用的人脸公开数据集,系统阐述了针对2维和3维数据特征点的自动定位方法,总结了各方法的研究现状及其应用,分析了当前人脸特征点自动定位技术在深度学习应用中的现状、存在问题及发展趋势。在公开的2维和3维人脸数据集上对不同方法进行了比较。通过研究可以看出,基于深度学习的2维人脸特征点的自动定位方法研究相对比较深入,而3维人脸特征点定位方法的研究在模型表示、处理方法和样本数量上都存在挑战。未来基于深度学习的3维人脸特征点定位方法将成为研究趋势。     

基于局部形状图的三维人脸特征点自动定位

准确定位人脸特征控制点是三维人脸识别的关键技术之一。提出了一种新的三维人脸特征点自动定位方法,结合局部形状索引与基于局部形状图(LSM)的统计模型,通过误差分析自适应地确定局部形状图的统计半径,实现任意姿态下的三维人脸鼻尖和内眼角的自动精确定位。在CASIA 3D人脸数据库的比较实验结果表明,该方法比基于先验信息和基于曲率分析的定位方法都具有更高的定位精确度。     

ASM及其改进的人脸面部特征定位算法

为了提高主动形状模型(ASM)算法的性能,提出一种改进的ASM算法.首先,精确定位出瞳孔的位置用作平均形状模型的初始化;其次,采用全局形状模型、面部显著特征区域成分形状模型以及人脸面部的相似性构形相结合的办法来共同约束特征点的定位结果;最后,特征点周围采用Log-Gabor小波系数进行描述,并建立局部纹理模型,提高了算法对光照和噪声的鲁棒性.实验结果表明,与传统的ASM算法相比,该算法特征点定位精确度有显著的提高.     

双目视觉下基于区域生长的三维人脸重建算法

为解决传统立体匹配算法匹配低纹理人脸图像时极易产生误匹配的问题,提出一种基于区域生长的人脸立体匹配算法。该算法利用级联回归树算法提取的人脸特征点将人脸划分为不同区域以分别限制各区域的视差搜索范围,从而避免在全局范围上查找匹配点;同时利用人脸的局部形状特性,采用局部曲面拟合的方式筛除误匹配种子点并生成大量可靠种子点用于区域生长;最后,分别在实验室环境采集的人脸图像和FRGC v2.0人脸数据库上进行定性和定量实验。实验结果表明,与传统算法相比,所提算法能够重建出更加准确的三维人脸模型。经点云配准后与人脸点云真实值的均方根误差在2 mm以内,且不同光照、姿态、表情下人脸图像的重建表明所改进的立体匹配算法具有较好的鲁棒性。