Summary
International Technical Conference on Circuits/Systems, Computers and Communications
2016
Session Number:P2
Session:
Number:P2-12
Face Frontalization Method using Depth Information
Xingjie Zhang, Joongseok Song, Jong-Il Park ,
pp.955-958
Publication Date:2016/7/10
Online ISSN:2188-5079
Summary:
Recently, the face recognition system has achieved excellent results. However, the performance of face recognition is affected by various factors such as expressions, occlusions and pose variations. And the pose variations is the most important one of these. In this paper, we propose a face frontalization technique which used face landmarks and depth information. This method could be applied in the preprocessing stage of the face recognition system and transform the non-fronted face to the front face. In experiments, we verified that a set of faces with various pose could be transformed to the front face by using proposed method.