Real-time face alignment enhancement by tracking
Tang Fanyang, Jianhua Zhang, Yujian Feng, Qiu Guan, Xiaolong Zhou · 2016
Face alignment is one of the most popular research areas in computer vision. It can be used in many fields, such as foundation of 3D-model of a face, face swap, face recognition. But most methods proposed were based on single images. In this paper, several strategies are proposed to enhance the performance of face alignment in videos. Through these strategies, three improvements have been achieved, including feature points stability, alignment of rolling face and the certainty of the detected face. To evaluate the proposed strategies, extensive experiments have been carried out and the results show that our strategies are effective.