Facial-feature detection and localization based on a hierarchical scheme.

Abstract: An efficient hierarchical scheme, which is robust to illumination and pose variations in face images, is proposed for accurate facial-feature detection and localization. In our algorithm, having detected a face region using a face detector, a wavelet-based saliency map – which can reflect the most visually meaningful regions – is computed on the detected face region. As the eye region always has the most variations in a face image, the coarse eye region can be reliably located based on the saliency map, and verified by means of principal component analysis. This step in the proposed hierarchical scheme narrows down the search space, thereby reducing the computational cost in the further precise localization of the two eye positions based on a pose-adapted eye template. Moreover, among the facial features, the eyes play the most important role, and their positions can be used as an approximate geometric reference to localize the other facial features. Therefore, localization of the nose and mouth can be determined by using the saliency values in the saliency map and the detected eye positions as geometric references. Our proposed algorithm is non-iterative and computationally simple. Experimental results show that our algorithm can achieve a superior performance compared to other state-of-the-art methods. [Copyright &y& Elsevier]