Facial action unit recognition by exploiting their dynamic and semantic relationships

A system that could automatically analyze the facial actions in real time has applications in a wide range of different fields. However, developing such a system is always challenging due to the richness, ambiguity, and the dynamic nature of facial actions. Although a number of research groups attempt to recognize facial action units (AUs) by either improving facial feature extraction techniques, or the AU classification techniques, these methods often recognize AUs or certain AU combinations individually and statically, ignoring the semantic relationships among AUs and the dynamics of AUs. Hence, these approaches cannot always recognize AUs reliably, robustly, and consistently.In this paper, we propose a novel approach that systematically accounts for the relationships among AUs and their temporal evolutions for AU recognition. Specifically, we use a dynamic Bayesian network (DBN) to model the relationships among different AUs. The DBN provides a coherent and unified hierarchical probabilistic framework to represent probabilistic relationships among various AUs and to account for the temporal changes in facial action development. Within our system, robust computer vision techniques are used to obtain AU measurements. And such AU measurements are then applied as evidence to the DBN for inferring various AUs. The experiments show that the integration of AU relationships and AU dynamics with AU measurements yields significant improvement of AU recognition, especially for spontaneous facial expressions and under more realistic environment including illumination variation, face pose variation, and occlusion.     

A Unified Probabilistic Framework for Spontaneous Facial Action Modeling and Understanding

Facial expression is a natural and powerful means of human communication. Recognizing spontaneous facial actions, however, is very challenging due to subtle facial deformation, frequent head movements, and ambiguous and uncertain facial motion measurements. Because of these challenges, current research in facial expression recognition is limited to posed expressions and often in frontal view. A spontaneous facial expression is characterized by rigid head movements and nonrigid facial muscular movements. More importantly, it is the coherent and consistent spatiotemporal interactions among rigid and nonrigid facial motions that produce a meaningful facial expression. Recognizing this fact, we introduce a unified probabilistic facial action model based on the Dynamic Bayesian network (DBN) to simultaneously and coherently represent rigid and nonrigid facial motions, their spatiotemporal dependencies, and their image measurements. Advanced machine learning methods are introduced to learn the model based on both training data and subjective prior knowledge. Given the model and the measurements of facial motions, facial action recognition is accomplished through probabilistic inference by systematically integrating visual measurements with the facial action model. Experiments show that compared to the state-of-the-art techniques, the proposed system yields significant improvements in recognizing both rigid and nonrigid facial motions, especially for spontaneous facial expressions.     

深度置信网络模型及应用研究综述

介绍深度置信网络（DBN）理论基础的发展,对比分析深层结构DBN与浅层网络结构的差异,最后引用多篇文献分析研究DBN在文字检测、人脸及表情识别领域和遥感图像领域的应用效果。全面介绍了深度学习模型DBN,深入分析DBN的构建与实际应用,为研究人员提供改进DBN的思路,以期在未来将其运用到更宽广的新兴领域中。     

Pain monitoring: A dynamic and context-sensitive system

The current paper presents an automatic and context sensitive system for the dynamic recognition of pain expression among the six basic facial expressions and neutral on acted and spontaneous sequences. A machine learning approach based on the Transferable Belief Model, successfully used previously to categorize the six basic facial expressions in static images [2], [61], is extended in the current paper for the automatic and dynamic recognition of pain expression from video sequences in a hospital context application. The originality of the proposed method is the use of the dynamic information for the recognition of pain expression and the combination of different sensors, permanent facial features behavior, transient features behavior, and the context of the study, using the same fusion model. Experimental results, on 2-alternative forced choices and, for the first time, on 8-alternative forced choices (i.e. pain expression is classified among seven other facial expressions), show good classification rates even in the case of spontaneous pain sequences. The mean classification rates on acted and spontaneous data reach 81.2% and 84.5% for the 2-alternative and 8-alternative forced choices, respectively. Moreover, the system performances compare favorably to the human observer rates (76%), and lead to the same doubt states in the case of blend expressions.     

Recognising facial expressions in video sequences

We introduce a system that processes a sequence of images of a front-facing human face and recognises a set of facial expressions. We use an efficient appearance-based face tracker to locate the face in the image sequence and estimate the deformation of its non-rigid components. The tracker works in real time. It is robust to strong illumination changes and factors out changes in appearance caused by illumination from changes due to face deformation. We adopt a model-based approach for facial expression recognition. In our model, an image of a face is represented by a point in a deformation space. The variability of the classes of images associated with facial expressions is represented by a set of samples which model a low-dimensional manifold in the space of deformations. We introduce a probabilistic procedure based on a nearest-neighbour approach to combine the information provided by the incoming image sequence with the prior information stored in the expression manifold to compute a posterior probability associated with a facial expression. In the experiments conducted we show that this system is able to work in an unconstrained environment with strong changes in illumination and face location. It achieves an 89% recognition rate in a set of 333 sequences from the Cohn–Kanade database.     

Recognition of facial expressions and measurement of levels of interest from video

This paper presents a spatio-temporal approach in recognizing six universal facial expressions from visual data and using them to compute levels of interest. The classification approach relies on a two-step strategy on the top of projected facial motion vectors obtained from video sequences of facial expressions. First a linear classification bank was applied on projected optical flow vectors and decisions made by the linear classifiers were coalesced to produce a characteristic signature for each universal facial expression. The signatures thus computed from the training data set were used to train discrete hidden Markov models (HMMs) to learn the underlying model for each facial expression. The performances of the proposed facial expressions recognition were computed using five fold cross-validation on Cohn-Kanade facial expressions database consisting of 488 video sequences that includes 97 subjects. The proposed approach achieved an average recognition rate of 90.9% on Cohn-Kanade facial expressions database. Recognized facial expressions were mapped to levels of interest using the affect space and the intensity of motion around apex frame. Computed level of interest was subjectively analyzed and was found to be consistent with "ground truth" information in most of the cases. To further illustrate the efficacy of the proposed approach, and also to better understand the effects of a number of factors that are detrimental to the facial expression recognition, a number of experiments were conducted. The first empirical analysis was conducted on a database consisting of 108 facial expressions collected from TV broadcasts and labeled by human coders for subsequent analysis. The second experiment (emotion elicitation) was conducted on facial expressions obtained from 21 subjects by showing the subjects six different movies clips chosen in a manner to arouse spontaneous emotional reactions that would produce natural facial expressions.     

多任务学习和对抗学习结合的自发与非自发表情识别

目的 如何提取与个体身份无关的面部特征以及建模面部行为的时空模式是自发与非自发表情识别的核心问题,然而现有的自发与非自发表情识别工作尚未同时兼顾两者。针对此,本文提出多任务学习和对抗学习结合的自发与非自发表情识别方法,通过多任务学习和对抗学习捕获面部行为的时空模式以及与学习身份无关的面部特征,实现有效的自发与非自发表情区分。方法 所提方法包括4部分：特征提取器、多任务学习器、身份判别器以及多任务判别器。特征提取器用来获取与自发和非自发表情相关的特征;身份判别器用来监督特征提取器学习到的特征,与身份标签无关;多任务学习器预测表情高峰帧相对于初始帧之间的特征点偏移量以及表情类别,并试图迷惑多任务判别器;多任务判别器辨别输入是真实的还是预测的人脸特征点偏移量与表情类别。通过多任务学习器和多任务判别器之间的对抗学习,捕获面部行为的时空模式。通过特征提取器、多任务学习器和身份判别器的协同学习,学习与面部行为有关而与个体身份无关的面部特征。结果 在MMI（M&M initiative）、NVIE（natural visible and infrared facial expression）和BioVid（biopotential and video）数据集上的实验结果表明本文方法可以学习出与个体身份相关性较低的特征,通过同时预测特征点偏移量和表情类别,有效捕获自发和非自发表情的时空模式,从而获得较好的自发与非自发表情识别效果。结论 实验表明本文所提出的基于对抗学习的网络不仅可以有效学习个体无关但表情相关的面部中特征,而且还可以捕捉面部行为中的空间模式,而这些信息可以很好地改善自发与非自发表情识别。     

Putting Objects in Perspective

Image understanding requires not only individually estimating elements of the visual world but also capturing the interplay among them. In this paper, we provide a framework for placing local object detection in the context of the overall 3D scene by modeling the interdependence of objects, surface orientations, and camera viewpoint. Most object detection methods consider all scales and locations in the image as equally likely. We show that with probabilistic estimates of 3D geometry, both in terms of surfaces and world coordinates, we can put objects into perspective and model the scale and location variance in the image. Our approach reflects the cyclical nature of the problem by allowing probabilistic object hypotheses to refine geometry and vice-versa. Our framework allows painless substitution of almost any object detector and is easily extended to include other aspects of image understanding. Our results confirm the benefits of our integrated approach.     

Emotion Detection via Discriminant Laplacian Embedding

Human emotion detection is of substantial importance in a variety of pervasive applications in assistive environments. Because facial expressions provide a key mechanism for understanding and conveying emotion, automatic emotion detection through facial expression recognition has attracted increased attention in both scientific research and practical applications in recent years. Traditional facial expression recognition methods normally use only one type of facial expression data, either static data extracted from one single face image or motion-dependent data obtained from dynamic face image sequences, but seldom employ both. This work proposes to place the emotion detection problem under the framework of Discriminant Laplacian Embedding (DLE) to integrate these two types of facial expression data in a shared subspace, such that the advantages of both of them are exploited. Due to the reinforcement between the two types of facial features, the new data representation is more discriminative and easier to classify. Encouraging experimental results in empirical studies demonstrate the practical usage of the proposed DLE method for emotion detection.     

Dynamics of facial expression: recognition of facial actions and their temporal segments from face profile image sequences.

Automatic analysis of human facial expression is a challenging problem with many applications. Most of the existing automated systems for facial expression analysis attempt to recognize a few prototypic emotional expressions, such as anger and happiness. Instead of representing another approach to machine analysis of prototypic facial expressions of emotion, the method presented in this paper attempts to handle a large range of human facial behavior by recognizing facial muscle actions that produce expressions. Virtually all of the existing vision systems for facial muscle action detection deal only with frontal-view face images and cannot handle temporal dynamics of facial actions. In this paper, we present a system for automatic recognition of facial action units (AUs) and their temporal models from long, profile-view face image sequences. We exploit particle filtering to track 15 facial points in an input face-profile sequence, and we introduce facial-action-dynamics recognition from continuous video input using temporal rules. The algorithm performs both automatic segmentation of an input video into facial expressions pictured and recognition of temporal segments (i.e., onset, apex, offset) of 27 AUs occurring alone or in a combination in the input face-profile video. A recognition rate of 87% is achieved.     

A novel database of children's spontaneous facial expressions (LIRIS-CSE)

Computing environment is moving towards human-centered designs instead of computer centered designs and human's tend to communicate wealth of information through affective states or expressions. Traditional Human Computer Interaction (HCI) based systems ignores bulk of information communicated through those affective states and just caters for user's intentional input. Generally, for evaluating and benchmarking different facial expression analysis algorithms, standardized databases are needed to enable a meaningful comparison. In the absence of comparative tests on such standardized databases it is difficult to find relative strengths and weaknesses of different facial expression recognition algorithms. In this article we present a novel video database for Children's Spontaneous facial Expressions (LIRIS-CSE). Proposed video database contains six basic spontaneous facial expressions shown by 12 ethnically diverse children between the ages of 6 and 12 years with mean age of 7.3 years. To the best of our knowledge, this database is first of its kind as it records and shows spontaneous facial expressions of children. Previously there were few database of children expressions and all of them show posed or exaggerated expressions which are different from spontaneous or natural expressions. Thus, this database will be a milestone for human behavior researchers. This database will be a excellent resource for vision community for benchmarking and comparing results. In this article, we have also proposed framework for automatic expression recognition based on Convolutional Neural Network (CNN) architecture with transfer learning approach. Proposed architecture achieved average classification accuracy of 75% on our proposed database i.e. LIRIS-CSE.     

融合时空域特征的人脸表情识别

目的 人脸表情识别是计算机视觉的核心问题之一。一方面,表情的产生对应着面部肌肉的一个连续动态变化过程,另一方面,该运动过程中的表情峰值帧通常包含了能够识别该表情的完整信息。大部分已有的人脸表情识别算法要么基于表情视频序列,要么基于单幅表情峰值图像。为此,提出了一种融合时域和空域特征的深度神经网络来分析和理解视频序列中的表情信息,以提升表情识别的性能。方法 该网络包含两个特征提取模块,分别用于学习单幅表情峰值图像中的表情静态“空域特征”和视频序列中的表情动态“时域特征”。首先,提出了一种基于三元组的深度度量融合技术,通过在三元组损失函数中采用不同的阈值,从单幅表情峰值图像中学习得到多个不同的表情特征表示,并将它们组合在一起形成一个鲁棒的且更具辩识能力的表情“空域特征”;其次,为了有效利用人脸关键组件的先验知识,准确提取人脸表情在时域上的运动特征,提出了基于人脸关键点轨迹的卷积神经网络,通过分析视频序列中的面部关键点轨迹,学习得到表情的动态“时域特征”;最后,提出了一种微调融合策略,取得了最优的时域特征和空域特征融合效果。结果 该方法在3个基于视频序列的常用人脸表情数据集CK+(the e...     

Audio-visual emotion fusion (AVEF): A deep efficient weighted approach

The multi-modal emotion recognition lacks the explicit mapping relation between emotion state and audio and image features, so extracting the effective emotion information from the audio/visual data is always a challenging issue. In addition, the modeling of noise and data redundancy is not solved well, so that the emotion recognition model is often confronted with the problem of low efficiency. The deep neural network (DNN) performs excellently in the aspects of feature extraction and highly non-linear feature fusion, and the cross-modal noise modeling has great potential in solving the data pollution and data redundancy. Inspired by these, our paper proposes a deep weighted fusion method for audio-visual emotion recognition. Firstly, we conduct the cross-modal noise modeling for the audio and video data, which eliminates most of the data pollution in the audio channel and the data redundancy in visual channel. The noise modeling is implemented by the voice activity detection(VAD), and the data redundancy in the visual data is solved through aligning the speech area both in audio and visual data. Then, we extract the audio emotion features and visual expression features via two feature extractors. The audio emotion feature extractor, audio-net, is a 2D CNN, which accepting the image-based Mel-spectrograms as input data. On the other hand, the facial expression feature extractor, visual-net, is a 3D CNN to which facial expression image sequence is feeded. To train the two convolutional neural networks on the small data set efficiently, we adopt the strategy of transfer learning. Next, we employ the deep belief network(DBN) for highly non-linear fusion of multi-modal emotion features. We train the feature extractors and the fusion network synchronously. And finally the emotion classification is obtained by the support vector machine using the output of the fusion network. With consideration of cross-modal feature fusion, denoising and redundancy removing, our fusion method show excellent performance on the selected data set.     

Simultaneous Facial Action Tracking and Expression Recognition in the Presence of Head Motion

The recognition of facial gestures and expressions in image sequences is an important and challenging problem. Most of the existing methods adopt the following paradigm. First, facial actions/features are retrieved from the images, then the facial expression is recognized based on the retrieved temporal parameters. In contrast to this mainstream approach, this paper introduces a new approach allowing the simultaneous retrieval of facial actions and expression using a particle filter adopting multi-class dynamics that are conditioned on the expression. For each frame in the video sequence, our approach is split into two consecutive stages. In the first stage, the 3D head pose is retrieved using a deterministic registration technique based on Online Appearance Models. In the second stage, the facial actions as well as the facial expression are simultaneously retrieved using a stochastic framework based on second-order Markov chains. The proposed fast scheme is either as robust as, or more robust than existing ones in a number of respects. We describe extensive experiments and provide evaluations of performance to show the feasibility and robustness of the proposed approach.     

基于生成式对抗网络的鲁棒人脸表情识别

人们在自然情感交流中经常伴随着头部旋转和肢体动作,它们往往导致较大范围的人脸遮挡,使得人脸图像损失部分表情信息.现有的表情识别方法大多基于通用的人脸特征和识别算法,未考虑表情和身份的差异,导致对新用户的识别不够鲁棒.本文提出了一种对人脸局部遮挡图像进行用户无关表情识别的方法.该方法包括一个基于Wasserstein生成式对抗网络（Wasserstein generative adversarial net,WGAN）的人脸图像生成网络,能够为图像中的遮挡区域生成上下文一致的补全图像;以及一个表情识别网络,能够通过在表情识别任务和身份识别任务之间建立对抗关系来提取用户无关的表情特征并推断表情类别.实验结果表明,我们的方法在由CK+,Multi-PIE和JAFFE构成的混合数据集上用户无关的平均识别准确率超过了90%.在CK+上用户无关的识别准确率达到了96%,其中4.5%的性能提升得益于本文提出的对抗式表情特征提取方法.此外,在45°头部旋转范围内,本文方法还能够用于提高非正面表情的识别准确率.     

基于特征运动的表情人脸识别

人脸像的面部表情识别一直是人脸识别的一个难点，为了提高表情人脸识别的鲁棒性，提出了一种基于特征运动的人脸识别方法，该方法首先利用块匹配的方法来确定表情人脸和无表情人脸之间的运动向量，然后利用主成分分析方法（PCA）从这些运动向量中，产生低维子空间，称之为特征运动空间，测试时，先将测试人脸与无表情人脸之间的运动向量投影到特征运动空间，再根据这个运动向量在特征运动空间里的残差进行人脸识别，同时还介绍了基于特征运动的个人模型方法和公共模型方法，实验结果证明，该新算法在表情人脸的识别上，优于特征脸方法，有非常高的识别率。     

Shape analysis of local facial patches for 3D facial expression recognition

In this paper we address the problem of 3D facial expression recognition. We propose a local geometric shape analysis of facial surfaces coupled with machine learning techniques for expression classification. A computation of the length of the geodesic path between corresponding patches, using a Riemannian framework, in a shape space provides a quantitative information about their similarities. These measures are then used as inputs to several classification methods. The experimental results demonstrate the effectiveness of the proposed approach. Using multiboosting and support vector machines (SVM) classifiers, we achieved 98.81% and 97.75% recognition average rates, respectively, for recognition of the six prototypical facial expressions on BU-3DFE database. A comparative study using the same experimental setting shows that the suggested approach outperforms previous work.     

Facial expression recognition – A real time approach

Face localization, feature extraction, and modeling are the major issues in automatic facial expression recognition. In this paper, a method for facial expression recognition is proposed. A face is located by extracting the head contour points using the motion information. A rectangular bounding box is fitted for the face region using those extracted contour points. Among the facial features, eyes are the most prominent features used for determining the size of a face. Hence eyes are located and the visual features of a face are extracted based on the locations of eyes. The visual features are modeled using support vector machine (SVM) for facial expression recognition. The SVM finds an optimal hyperplane to distinguish different facial expressions with an accuracy of 98.5%.     

Interactive visual analysis of time-series microarray data

Estimating dynamic regulatory pathways using DNA microarray time-series can provide invaluable information about the dynamic interactions among genes and result in new methods of rational drug design. Even though several purely computational methods have been introduced for DNA pathway analysis, most of these techniques do not provide a fully interactive method to explore and analyze these dynamic interactions in detail, which is necessary to obtain a full understanding. In this paper, we present a unified modeling and visual approach focusing on visual analysis of gene regulatory pathways over time. As a preliminary step in analyzing the gene interactions, the method applies two different techniques, a clustering algorithm and an auto regressive (AR) model. This approach provides a successful prediction of the dynamic pathways involved in the biological process under study. At this level, these pure computational techniques lack the transparency required for analysis and understanding of the gene interactions. To overcome the limitations, we have designed a visual analysis method that applies several visualization techniques, including pixel-based gene representation, animation, and multi-dimensional scaling (MDS), in a new way. This visual analysis framework allows the user to quickly and thoroughly search for and find the dynamic interactions among genes, highlight interesting gene information, show the detailed annotations of the selected genes, compare regulatory behaviors for different genes, and support gene sequence analysis for the interesting genes. In order to enhance these analysis capabilities, several methods are enabled, providing a simple graph display, a pixel-based gene visualization technique, and a relation-displaying technique among gene expressions and gene regulatory pathways.