Temporal Segmentation of Facial Behavior in Static Images Using HOG & Piecewise Linear SVM

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. This paper consists of efficient facial detection in static images using Histogram of Oriented Gradients (HOG) for local feature extraction and linear piecewise support vector machine (PL-SVM) classifiers. Histogram of oriented gradient (HOG) gives an accurate description of the contour of image. HOG features are calculated by taking orientation of histogram of edge intensity in a local region. PL-SVM is nonlinear classifier that can discriminate multi-view and multi-posture from the images in high dimensional feature space. Each PL-SVM model forms the subspace, corresponding to the cluster of special view. This paper consists of comparison of PL-SVM and several recent SVM methods in terms of cross validation accuracy.