Michel F. Valstar

Web-based database for facial expression analysis

In the last decade, the research topic of automatic analysis of facial expressions has become a central topic in machine vision research. Nonetheless, there is a glaring lack of a comprehensive, readily accessible reference set of face images that could be used as a basis for benchmarks for efforts in the field. This lack of easily accessible, suitable, common testing resource forms the major impediment to comparing and extending the issues concerned with automatic facial expression analysis. In this paper, we discuss a number of issues that make the problem of creating a benchmark facial expression database difficult. We then present the MMI facial expression database, which includes more than 1500 samples of both static images and image sequences of faces in frontal and in profile view displaying various expressions of emotion, single and multiple facial muscle activation. It has been built as a Web-based direct-manipulation application, allowing easy access and easy search of the available images. This database represents the most comprehensive reference set of images for studies on facial expression analysis to date.

Fully Automatic Facial Action Unit Detection and Temporal Analysis

In this work we report on the progress of building a system that enables fully automated fast and robust facial expression recognition from face video. We analyse subtle changes in facial expression by recognizing facial muscle action units (AUs) and analysing their temporal behavior. By detecting AUs from face video we enable the analysis of various facial communicative signals including facial expressions of emotion, attitude and mood. For an input video picturing a facial expression we detect per frame whether any of 15 different AUs is activated, whether that facial action is in the onset, apex, or offset phase, and what the total duration of the activation in question is. We base this process upon a set of spatio-temporal features calculated from tracking data for 20 facial fiducial points. To detect these 20 points of interest in the first frame of an input face video, we utilize a fully automatic, facial point localization method that uses individual feature GentleBoost templates built from Gabor wavelet features. Then, we exploit a particle filtering scheme that uses factorized likelihoods and a novel observation model that combines a rigid and a morphological model to track the facial points. The AUs displayed in the input video and their temporal segments are recognized finally by Support Vector Machines trained on a subset of most informative spatio-temporal features selected by AdaBoost. For Cohn-Kanade andMMI databases, the proposed system classifies 15 AUs occurring alone or in combination with other AUs with a mean agreement rate of 90.2% with human FACS coders.

The first facial expression recognition and analysis challenge

Automatic Facial Expression Recognition and Analysis, in particular FACS Action Unit (AU) detection and discrete emotion detection, has been an active topic in computer science for over two decades. Standardisation and comparability has come some way; for instance, there exist a number of commonly used facial expression databases. However, lack of a common evaluation protocol and lack of sufficient details to reproduce the reported individual results make it difficult to compare systems to each other. This in turn hinders the progress of the field. A periodical challenge in Facial Expression Recognition and Analysis would allow this comparison in a fair manner. It would clarify how far the field has come, and would allow us to identify new goals, challenges and targets. In this paper we present the first challenge in automatic recognition of facial expressions to be held during the IEEE conference on Face and Gesture Recognition 2011, in Santa Barbara, California. Two sub-challenges are defined: one on AU detection and another on discrete emotion detection. It outlines the evaluation protocol, the data used, and the results of a baseline method for the two sub-challenges.

Facial point detection using boosted regression and graph models

Finding fiducial facial points in any frame of a video showing rich naturalistic facial behaviour is an unsolved problem. Yet this is a crucial step for geometric-feature-based facial expression analysis, and methods that use appearance-based features extracted at fiducial facial point locations. In this paper we present a method based on a combination of Support Vector Regression and Markov Random Fields to drastically reduce the time needed to search for a points location and increase the accuracy and robustness of the algorithm. Using Markov Random Fields allows us to constrain the search space by exploiting the constellations that facial points can form. The regressors on the other hand learn a mapping between the appearance of the area surrounding a point and the positions of these points, which makes detection of the points very fast and can make the algorithm robust to variations of appearance due to facial expression and moderate changes in head pose. The proposed point detection algorithm was tested on 1855 images, the results of which showed we outperform current state of the art point detectors.

Fully Automatic Recognition of the Temporal Phases of Facial Actions

Past work on automatic analysis of facial expressions has focused mostly on detecting prototypic expressions of basic emotions like happiness and anger. The method proposed here enables the detection of a much larger range of facial behavior by recognizing facial muscle actions [action units (AUs)] that compound expressions. AUs are agnostic, leaving the inference about conveyed intent to higher order decision making (e.g., emotion recognition). The proposed fully automatic method not only allows the recognition of 22 AUs but also explicitly models their temporal characteristics (i.e., sequences of temporal segments: neutral, onset, apex, and offset). To do so, it uses a facial point detector based on Gabor-feature-based boosted classifiers to automatically localize 20 facial fiducial points. These points are tracked through a sequence of images using a method called particle filtering with factorized likelihoods. To encode AUs and their temporal activation models based on the tracking data, it applies a combination of GentleBoost, support vector machines, and hidden Markov models. We attain an average AU recognition rate of 95.3% when tested on a benchmark set of deliberately displayed facial expressions and 72% when tested on spontaneous expressions.

The SEMAINE corpus of emotionally coloured character interactions

We have recorded a new corpus of emotionally coloured conversations. Users were recorded while holding conversations with an operator who adopts in sequence four roles designed to evoke emotional reactions. The operator and the user are seated in separate rooms; they see each other through teleprompter screens, and hear each other through speakers. To allow high quality recording, they are recorded by five high-resolution, high framerate cameras, and by four microphones. All sensor information is recorded synchronously, with an accuracy of 25 μs. In total, we have recorded 20 participants, for a total of 100 character conversational and 50 non-conversational recordings of approximately 5 minutes each. All recorded conversations have been fully transcribed and annotated for five affective dimensions and partially annotated for 27 other dimensions. The corpus has been made available to the scientific community through a web-accessible database.

AVEC 2011-the first international audio/visual emotion challenge

The Audio/Visual Emotion Challenge and Workshop (AVEC 2011) is the first competition event aimed at comparison of multimedia processing and machine learning methods for automatic audio, visual and audiovisual emotion analysis, with all participants competing under strictly the same conditions. This paper first describes the challenge participation conditions. Next follows the data used - the SEMAINE corpus - and its partitioning into train, development, and test partitions for the challenge with labelling in four dimensions, namely activity, expectation, power, and valence. Further, audio and video baseline features are introduced as well as baseline results that use these features for the three sub-challenges of audio, video, and audiovisual emotion recognition.

Meta-Analysis of the First Facial Expression Recognition Challenge

Automatic facial expression recognition has been an active topic in computer science for over two decades, in particular facial action coding system action unit (AU) detection and classification of a number of discrete emotion states from facial expressive imagery. Standardization and comparability have received some attention; for instance, there exist a number of commonly used facial expression databases. However, lack of a commonly accepted evaluation protocol and, typically, lack of sufficient details needed to reproduce the reported individual results make it difficult to compare systems. This, in turn, hinders the progress of the field. A periodical challenge in facial expression recognition would allow such a comparison on a level playing field. It would provide an insight on how far the field has come and would allow researchers to identify new goals, challenges, and targets. This paper presents a meta-analysis of the first such challenge in automatic recognition of facial expressions, held during the IEEE conference on Face and Gesture Recognition 2011. It details the challenge data, evaluation protocol, and the results attained in two subchallenges: AU detection and classification of facial expression imagery in terms of a number of discrete emotion categories. We also summarize the lessons learned and reflect on the future of the field of facial expression recognition in general and on possible future challenges in particular.

AVEC 2013: the continuous audio/visual emotion and depression recognition challenge

Mood disorders are inherently related to emotion. In particular, the behaviour of people suffering from mood disorders such as unipolar depression shows a strong temporal correlation with the affective dimensions valence and arousal. In addition, psychologists and psychiatrists take the observation of expressive facial and vocal cues into account while evaluating a patients condition. Depression could result in expressive behaviour such as dampened facial expressions, avoiding eye contact, and using short sentences with flat intonation. It is in this context that we present the third Audio-Visual Emotion recognition Challenge (AVEC 2013). The challenge has two goals logically organised as sub-challenges: the first is to predict the continuous values of the affective dimensions valence and arousal at each moment in time. The second sub-challenge is to predict the value of a single depression indicator for each recording in the dataset. This paper presents the challenge guidelines, the common data used, and the performance of the baseline system on the two tasks.

Facial Action Unit Detection using Probabilistic Actively Learned Support Vector Machines on Tracked Facial Point Data

A system that could enable fast and robust facial expression recognition would have many applications in behavioral science, medicine, security and human-machine interaction. While working toward that goal, we do not attempt to recognize prototypic facial expressions of emotions but analyze subtle changes in facial behavior by recognizing facial muscle action units (AUs, i.e., atomic facial signals) instead. By detecting AUs we can analyse many more facial communicative signals than emotional expressions alone. This paper proposes AU detection by classifying features calculated from tracked ?ducial facial points. We use a Particle Filtering tracking scheme using factorized likelihoods and a novel observation model that combines a rigid and a morphologic model. The AUs displayed in a video are classi?ed using Probabilistic Actively Learned Support VectorMachines (PAL-SVM).When tested on 167 videos from the MMI web-based facial expression database, the proposed method achieved very high recognition rates for 16 different AUs. To ascertain data independency we also performed a validation using another benchmark database. When trained on the MMI-Facial expression database and tested on the Cohn-Kanade database, the proposed method achieved a recognition rate of 84% when detecting 9 AUs occurring alone or in combination in input image sequences.