Face recognition based on recurrent regression neural network

To address the sequential changes of images including poses, in this paper we propose a recurrent regression neural network (RRNN) framework to unify two classic tasks of cross-pose face recognition on still images and videos. To imitate the changes of images, we explicitly construct the potential dependencies of sequential images so as to regularizing the final learning model. By performing progressive transforms for sequentially adjacent images, RRNN can adaptively memorize and forget the information that benefits for the final classification. For face recognition of still images, given any one image with any one pose, we recurrently predict the images with its sequential poses to expect to capture some useful information of other poses. For video-based face recognition, the recurrent regression takes one entire sequence rather than one image as its input. We verify RRNN in still face image dataset MultiPIE and face video dataset YouTube Celebrities (YTC). The comprehensive experimental results demonstrate the effectiveness of the proposed RRNN method.