Facial Shape Analysis Under Complex Conditions

Face recognition is one of the most popular applications in the computer science research field。Face alignment and facial features localization are two key factors in the field of face recognition, and also are big challenges.Geometric normalization is an important approach to exploit the regularity of face images, by constructing the semantic correspondence between facial features, removing or reducing some variations caused by the changes of pose, scale, expression and so on. In this paper, a novel face normalization method is presented based on the congealing method. Congealing is a recently proposed normalization method which learns a particular affine transformation for each face image such that the entropy of a group of face images is minimized. However, this method does not employ the intrinsic characteristic of face images and needs a time-consuming offline training procedure. We improve on this by training it in a supervised manner and learning the affine transform based on the locations of eyes in a given images, which results in an efficient geometrical face normalization algorithm with eye localizations as byproduct. Experiments on the challenging Labeled Faces in the Wild database show that our method is superior to the original congealing method in terms of recognition performance.Active shape model, as a very popular method for object localization, has achieved great success in facial features localization. However, traditional active shape model has its own restrict. We improve the model by better initial shape locations and a better model on local texture. First, we use eye localization to get a better initial model shape. Second, we construct a more robust local appearance model with local information of each landmark fully. The experiments on AR face database indicate that the our method has improved the robustness and accuracy in facial features localization.