Shigeru Akamatsu

Comparison between geometry-based and Gabor-wavelets-based facial expression recognition using multi-layer perceptron

The authors investigate the use of two types of features extracted from face images for recognizing facial expressions. The first type is the geometric positions of a set of fiducial points on a face. The second type is a set of multi-scale and multi-orientation Gabor wavelet coefficients extracted from the face image at the fiducial points. They can be used either independently or jointly. The architecture developed is based on a two-layer perceptron. The recognition performance with different types of features has been compared, which shows that Gabor wavelet coefficients are much more powerful than geometric positions. Furthermore, since the first layer of the perceptron actually performs a nonlinear reduction of the dimensionality of the feature space, they have also studied the desired number of hidden units, i.e., the appropriate dimension to represent a facial expression in order to achieve a good recognition rate. It turns out that five to seven hidden units are probably enough to represent the space of feature expressions.

Head pose determination from one image using a generic model

We present a new method for determining the pose of a human head from its 2D image. It does not use any artificial markers put on a face. The basic idea is to use a generic model of a human head, which accounts for variation in shape and facial expression. Particularly, a set of 3D curves are used to model the contours of eyes, lips and eyebrows. A technique called iterative closest curve matching (ICC) is proposed, which aims at recovering the pose by iteratively minimizing the distances between the projected model curves and their closest image curves. Because curves contain richer information (such as curvature and length) than points, ICC is both more robust and more efficient than the well-known iterative closest point matching techniques (ICP). Furthermore, the image can be taken by a camera with unknown internal parameters, which can be recovered by our technique thanks to the 3D model. Preliminary experiments show that the proposed technique is promising and that an accurate pose estimate can be obtained from just one image with a generic head model.