Tingfan Wu

The computer expression recognition toolbox (CERT)

We present the Computer Expression Recognition Toolbox (CERT), a software tool for fully automatic real-time facial expression recognition, and officially release it for free academic use. CERT can automatically code the intensity of 19 different facial actions from the Facial Action Unit Coding System (FACS) and 6 different protoypical facial expressions. It also estimates the locations of 10 facial features as well as the 3-D orientation (yaw, pitch, roll) of the head. On a database of posed facial expressions, Extended Cohn-Kanade (CK+ [1]), CERT achieves an average recognition performance (probability of correctness on a two-alternative forced choice (2AFC) task between one positive and one negative example) of 90.1% when analyzing facial actions. On a spontaneous facial expression dataset, CERT achieves an accuracy of nearly 80%. In a standard dual core laptop, CERT can process 320 × 240 video images in real time at approximately 10 frames per second.

Facial expression recognition using Gabor motion energy filters

Spatial Gabor energy filters (GE) are one of the most successful approaches to represent facial expressions in computer vision applications, including face recognition and expression analysis. It is well known that these filters approximate the response of complex cells in primary visual cortex. However these neurons are modulated by the temporal, not just spatial, properties of the visual signal. This suggests that spatio-temporal Gabor filters may provide useful representations for applications that involve video sequences. In this paper we explore Gabor motion energy filters (GME) as a biologically inspired representation for dynamic facial expressions. Experiments on the Cohn-Kanade expression dataset show that GME outperforms GE, particularly on difficult low intensity expression discrimination.

Exploring bag of words architectures in the facial expression domain

Automatic facial expression recognition (AFER) has undergone substantial advancement over the past two decades. This work explores the application of bag of words (BoW), a highly matured approach for object and scene recognition to AFER. We proceed by first highlighting the reasons that makes the task for BoW differ for AFER compared to object and scene recognition. We propose suitable extensions to BoW architecture for the AFERs task. These extensions are able to address some of the limitations of current state of the art appearance-based approaches to AFER. Our BoW architecture is based on the spatial pyramid framework, augmented by multiscale dense SIFT features, and a recently proposed approach for object classification: locality-constrained linear coding and max-pooling. Combining these, we are able to achieve a powerful facial representation that works well even with linear classifiers. We show that a well designed BoW architecture can provide a performance benefit for AFER, and elements of the proposed BoW architecture are empirically evaluated. The proposed BoW approach supersedes previous state of the art results by achieving an average recognition rate of 96% on AFER for two public datasets.

Learning to Make Facial Expressions

This paper explores the process of self-guided learning of realistic facial expression production by a robotic head with 31 degrees of freedom. Facial motor parameters were learned using feedback from real-time facial expression recognition from video. The experiments show that the mapping of servos to expressions was learned in under one-hour of training time. We discuss how our work may help illuminate the computational study of how infants learn to make facial expressions.

Computer Expression Recognition Toolbox

We present a live demo of the Computer Expression Recognition Toolbox (CERT) developed at University of California, San Diego. CERT measures facial expressions in real-time, and codes them with respect to expressions of basic emotion, as well as over 20 facial actions from the Facial Action Coding System (Ekman & Friesen, 1978). Head pose (yaw, pitch, and roll) is also detected using an algorithm presented at this conference (Whitehill & Movellan, 2008). A sample output is shown in Figure 1.

Multilayer Architectures for Facial Action Unit Recognition

In expression recognition and many other computer vision applications, the recognition performance is greatly improved by adding a layer of nonlinear texture filters between the raw input pixels and the classifier. The function of this layer is typically known as feature extraction. Popular filter types for this layer are Gabor energy filters (GEFs) and local binary patterns (LBPs). Recent work [1] suggests that adding a second layer of nonlinear filters on top of the first layer may be beneficial. However, it is unclear what is the best architecture of layers and selection of filters. In this paper, we present a thorough empirical analysis of the performance of single-layer and dual-layer texture-based approaches for action unit recognition. For the single hidden layer case, GEFs perform consistently better than LBPs, which may be due to their robustness to jitter and illumination noise as well as to their ability to encode texture at multiple resolutions. For dual-layer case, we confirm that, while small, the benefit of adding this second layer is reliable and consistent across data sets. Interestingly for this second layer, LBPs appear to perform better than GEFs.

Letters: Learning spatiotemporal features by using independent component analysis with application to facial expression recognition

Engineered features have been heavily employed in computer vision. Recently, feature learning from unlabeled data for improving the performance of a given vision task has received increasing attention in both machine learning and computer vision. In this paper, we present using unlabeled video data to learn spatiotemporal features for video classification tasks. Specifically, we employ independent component analysis (ICA) to learn spatiotemporal filters from natural videos, and then construct feature representations for the input videos in classification tasks based on the learned filters. We test the performance of proposed feature learning method with application to facial expression recognition. The experimental results on the well-known Cohn-Kanade database show that the learned features perform better than engineered features. The comparison experiments on recognition of low intensity expressions show that our method yields a better performance than spatiotemporal Gabor features.

Action unit recognition transfer across datasets

We explore how CERT [15], a computer expression recognition toolbox trained on a large dataset of spontaneous facial expressions (FFD07), generalizes to a new, previously unseen dataset (FERA). The experiment was unique in that the authors had no access to the test labels, which were guarded as part of the FERA challenge. We show that without any training or special adaptation to the new database, CERT performs better than a baseline method trained exclusively on that database. Best results are achieved by retraining CERT with a combination of old and new data. We also found that the FERA dataset may be too small and idiosyncratic to generalize to other datasets. Training on FERA alone produced good results on FERA but very poor results on FFD07. We reflect on the importance of challenges like this for the future of the field, and discuss suggestions for standardization of future challenges.

The motion in emotion — A CERT based approach to the FERA emotion challenge

This paper assesses the performance of measures of facial expression dynamics derived from the Computer Expression Recognition Toolbox (CERT) for classifying emotions in the Facial Expression Recognition and Analysis (FERA) Challenge. The CERT system automatically estimates facial action intensity and head position using learned appearance-based models on single frames of video. CERT outputs were used to derive a representation of the intensity and motion in each video, consisting of the extremes of displacement, velocity and acceleration. Using this representation, emotion detectors were trained on the FERA training examples. Experiments on the released portion of the FERA dataset are presented, as well as results on the blind test. No consideration of subject identity was taken into account in the blind test. The F1 scores were well above the baseline criterion for success.

Modeling and identification of pneumatic actuators

Pneumatic actuators are mechanically simple and robust, have good energetic properties due to air compressibility, and are relatively cheap. Despite these advantages they are difficult to control - pressure dynamics have typical timescales on the order of 100ms, and this delay can severely cripple simplistic control approaches. The solution is to use a model-based controller with a good model of the pressure dynamics. Here we present a general parametric model of these dynamics based on both a theoretical analysis and an empirical study with a humanoid robot.