F. De la Torre

Face recognition using Histograms of Oriented Gradients

Face recognition has been a long standing problem in computer vision. Recently, Histograms of Oriented Gradients (HOGs) have proven to be an effective descriptor for object recognition in general and face recognition in particular. In this paper, we investigate a simple but powerful approach to make robust use of HOG features for face recognition. The three main contributions of this work are: First, in order to compensate for errors in facial feature detection due to occlusions, pose and illumination changes, we propose to extract HOG descriptors from a regular grid. Second, fusion of HOG descriptors at different scales allows to capture important structure for face recognition. Third, we identify the necessity of performing dimensionality reduction to remove noise and make the classification process less prone to overfitting. This is particularly important if HOG features are extracted from overlapping cells. Finally, experimental results on four databases illustrate the benefits of our approach.

Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion

Temporal segmentation of human motion into plausible motion primitives is central to understanding and building computational models of human motion. Several issues contribute to the challenge of discovering motion primitives: the exponential nature of all possible movement combinations, the variability in the temporal scale of human actions, and the complexity of representing articulated motion. We pose the problem of learning motion primitives as one of temporal clustering, and derive an unsupervised hierarchical bottom-up framework called hierarchical aligned cluster analysis (HACA). HACA finds a partition of a given multidimensional time series into m disjoint segments such that each segment belongs to one of k clusters. HACA combines kernel k-means with the generalized dynamic time alignment kernel to cluster time series data. Moreover, it provides a natural framework to find a low-dimensional embedding for time series. HACA is efficiently optimized with a coordinate descent strategy and dynamic programming. Experimental results on motion capture and video data demonstrate the effectiveness of HACA for segmenting complex motions and as a visualization tool. We also compare the performance of HACA to state-of-the-art algorithms for temporal clustering on data of a honey bee dance. The HACA code is available online.

A Least-Squares Framework for Component Analysis

Over the last century, Component Analysis (CA) methods such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Canonical Correlation Analysis (CCA), Locality Preserving Projections (LPP), and Spectral Clustering (SC) have been extensively used as a feature extraction step for modeling, classification, visualization, and clustering. CA techniques are appealing because many can be formulated as eigen-problems, offering great potential for learning linear and nonlinear representations of data in closed-form. However, the eigen-formulation often conceals important analytic and computational drawbacks of CA techniques, such as solving generalized eigen-problems with rank deficient matrices (e.g., small sample size problem), lacking intuitive interpretation of normalization factors, and understanding commonalities and differences between CA methods. This paper proposes a unified least-squares framework to formulate many CA methods. We show how PCA, LDA, CCA, LPP, SC, and its kernel and regularized extensions correspond to a particular instance of least-squares weighted kernel reduced rank regression (LS--WKRRR). The LS-WKRRR formulation of CA methods has several benefits: 1) provides a clean connection between many CA techniques and an intuitive framework to understand normalization factors; 2) yields efficient numerical schemes to solve CA techniques; 3) overcomes the small sample size problem; 4) provides a framework to easily extend CA methods. We derive weighted generalizations of PCA, LDA, SC, and CCA, and several new CA techniques.

Model-Based Face De-Identification

Advances in camera and computing equipment hardware in recent years have made it increasingly simple to capture and store extensive amounts of video data. This, among other things, creates ample opportunities for the sharing of video sequences. In order to protect the privacy of subjects visible in the scene, automated methods to de-identify the images, particularly the face region, are necessary. So far the majority of privacy protection schemes currently used in practice rely on ad-hoc methods such as pixelation or blurring of the face. In this paper we show in extensive experiments that pixelation and blurring offers very poor privacy protection while significantly distorting the data. We then introduce a novel framework for de-identifying facial images. Our algorithm combines a model-based face image parameterization with a formal privacy protection model. In experiments on two large-scale data sets we demonstrate privacy protection and preservation of data utility.

Temporal Segmentation of Facial Behavior

Temporal segmentation of facial gestures in spontaneous facial behavior recorded in real-world settings is an important, unsolved, and relatively unexplored problem in facial image analysis. Several issues contribute to the challenge of this task. These include non-frontal pose, moderate to large out-of-plane head motion, large variability in the temporal scale of facial gestures, and the exponential nature of possible facial action combinations. To address these challenges, we propose a two-step approach to temporally segment facial behavior. The first step uses spectral graph techniques to cluster shape and appearance features invariant to some geometric transformations. The second step groups the clusters into temporally coherent facial gestures. We evaluated this method in facial behavior recorded during face-to- face interactions. The video data were originally collected to answer substantive questions in psychology without concern for algorithm development. The method achieved moderate convergent validity with manual FACS (Facial Action Coding System) annotation. Further, when used to preprocess video for manual FACS annotation, the method significantly improves productivity, thus addressing the need for ground-truth data for facial image analysis. Moreover, we were also able to detect unusual facial behavior.

Representational oriented component analysis (ROCA) for face recognition with one sample image per training class

Subspace methods such as PCA, LDA, ICA have become a standard tool to perform visual learning and recognition. In this paper we propose representational oriented component analysis (ROCA), an extension of OCA, to perform face recognition when just one sample per training class is available. Several novelties are introduced in order to improve generalization and efficiency: (1) combining several OCA classifiers based on different image representations of the unique training sample is shown to greatly improve the recognition performance. (2) To improve generalization and to account for small misregistration effect, a learned subspace is added to constrain the OCA solution, (3) a stable/efficient generalized eigenvector algorithm that solves the small size sample problem and avoids overfitting. Preliminary experiments in the FRGC Ver 1.0 dataset show that ROCA outperforms existing linear techniques (PCA, OCA) and some commercial systems.

A probabilistic framework for rigid and non-rigid appearance based tracking and recognition

This paper describes an unified probabilistic framework for appearance-based tracking of rigid and non-rigid objects. A spatio-temporal dependent shape-texture eigenspace and mixture of diagonal Gaussians are learned in a hidden Markov model (HMM)-like structure to better constrain the model and for recognition purposes. Particle filtering is used to track the object while switching between different shape/texture models. This framework allows recognition and temporal segmentation of activities. Additionally an automatic stochastic initialization is proposed, the number of states in the HMM are selected based on the Akaike information criterion and comparison with deterministic tracking for 2D models is discussed. Preliminary results of eye tracking, lip tracking and temporal segmentation of mouth events are presented.

Parameterized Kernel Principal Component Analysis: Theory and applications to supervised and unsupervised image alignment

Parameterized appearance models (PAMs) (e.g. eigen-tracking, active appearance models, morphable models) use principal component analysis (PCA) to model the shape and appearance of objects in images. Given a new image with an unknown appearance/shape configuration, PAMs can detect and track the object by optimizing the modelpsilas parameters that best match the image. While PAMs have numerous advantages for image registration relative to alternative approaches, they suffer from two major limitations: First, PCA cannot model non-linear structure in the data. Second, learning PAMs requires precise manually labeled training data. This paper proposes parameterized kernel principal component analysis (PKPCA), an extension of PAMs that uses Kernel PCA (KPCA) for learning a non-linear appearance model invariant to rigid and/or non-rigid deformations. We demonstrate improved performance in supervised and unsupervised image registration, and present a novel application to improve the quality of manual landmarks in faces. In addition, we suggest a clean and effective matrix formulation for PKPCA.

Dynamic Cascades with Bidirectional Bootstrapping for Action Unit Detection in Spontaneous Facial Behavior

Automatic facial action unit detection from video is a long-standing problem in facial expression analysis. Research has focused on registration, choice of features, and classifiers. A relatively neglected problem is the choice of training images. Nearly all previous work uses one or the other of two standard approaches. One approach assigns peak frames to the positive class and frames associated with other actions to the negative class. This approach maximizes differences between positive and negative classes, but results in a large imbalance between them, especially for infrequent AUs. The other approach reduces imbalance in class membership by including all target frames from onsets to offsets in the positive class. However, because frames near onsets and offsets often differ little from those that precede them, this approach can dramatically increase false positives. We propose a novel alternative, dynamic cascades with bidirectional bootstrapping (DCBB), to select training samples. Using an iterative approach, DCBB optimally selects positive and negative samples in the training data. Using Cascade Adaboost as basic classifier, DCBB exploits the advantages of feature selection, efficiency, and robustness of Cascade Adaboost. To provide a real-world test, we used the RU-FACS (a.k.a. M3) database of nonposed behavior recorded during interviews. For most tested action units, DCBB improved AU detection relative to alternative approaches.

Facial feature detection with optimal pixel reduction SVM

Automatic facial feature localization has been a long-standing challenge in the field of computer vision for several decades. This can be explained by the large variation a face in an image can have due to factors such as position, facial expression, pose, illumination, and background clutter. Support Vector Machines (SVMs) have been a popular statistical tool for facial feature detection. Traditional SVM approaches to facial feature detection typically extract features from images (e.g. multiband filter, SIFT features) and learn the SVM parameters. Independently learning features and SVM parameters might result in a loss of information related to the classification process. This paper proposes an energy-based framework to jointly perform relevant feature weighting and SVM parameter learning. Preliminary experiments on standard face databases have shown significant improvement in speed with our approach.