Description

The tracking and recognition of facial activities from images or videos have attracted great attention in computer vision field. Facial activities are characterized by three levels. First, in the bottom level, facial feature points around each facial component, i.e., eyebrow, mouth, etc., capture the detailed face shape information. Second, in the middle level, facial action units, defined in the facial action coding system, represent the contraction of a specific set of facial muscles, i.e., lid tightener, eyebrow raiser, etc. Finally, in the top level, six prototypical facial expressions represent the global facial muscle movement and are commonly used to describe the human emotion states. In contrast to the mainstream approaches, which usually only focus on one or two levels of facial activities, and track (or recognize) them separately, this paper introduces a unified probabilistic framework based on the dynamic Bayesian network to simultaneously and coherently represent the facial evolvement in different levels, their interactions and their observations. Facial feature points encode critical information about face shape and face shape deformation. Accurate location and tracking of facial feature points are important in the applications such as animation, computer graphics, etc. Generally, the facial feature points tracking technologies could be classified into two categories: model free and model-based tracking algorithms. The recognition of the persons from images has numerous applications in Image Surveillances and Computer Vision. Face detection in still images is applied in many of the devices and in many of the applications. Face detection in images is a recent technique which ensures the identification of person in the image. In a image normally the pose of the persons and the illumination variations were normally present. The main challenge of detecting face images in images is the pose and the illumination variations and sudden changes in the movement of the object. The images taken from cameras are taken. The surveillance images were normally not so clear and there may be some illumination variations and blurness at some places due to rapid movement of the objects. The proposed system analyzes and recognizes the exact face image from the image while the existing systems deals with the recognition of the face images from still images. The proposed system is capable of identifying the face images in the image in a better manner even though there are pose variations illumination variations and blurs occurring due to rapid motions of the subjects in the image.