In this paper, an approach for pose invariant face detection is proposed by estimating the pose of detected face image. The approach comprises of detection of frontal and profile faces, followed by degree of freedom (DoF) identification and accurate estimation of pose. For pose invariant face detection, cascaded structure of Haar-like features along with adaboost classification has been used in this paper. The detected face image forms the input for DoF identification and poses estimation. The identification of DoF involves the classification of pose as Roll, Pitch and Yaw orientations. The DoF is identified by using proposed optimized Haar-like features and random forest classifier. For pose estimation, Haar based descriptor is constructed to have an efficient estimation of the angle of rotation in Roll, Pitch and Yaw. Haar based descriptor with weighted voting algorithm gives the final estimate of pose. The accuracy of the proposed system is found to be efficient than the existing work.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.