A general framework for face reconstruction using single still image based on 2D-to-3D transformation kernel

作者：Fooprateepsiri Rerkchai^*; Kurutach Werasak

来源：Forensic Science International, 2014, 236: 117-126.

DOI：10.1016/j.forsciint.2013.12.020

• Face reconstruction
• Face detection
• Face recognition
• View synthesis
• Gradient vector flow

Face authentication is a biometric classification method that verifies the identity of a user based on image of their face. Accuracy of the authentication is reduced when the pose, illumination and expression of the training face images are different than the testing image. The methods in this paper are designed to improve the accuracy of a features-based face recognition system when the pose between the input images and training images are different. First, an efficient 2D-to-3D integrated face reconstruction approach is introduced to reconstruct a personalized 3D face model from a single frontal face image with neutral expression and normal illumination. Second, realistic virtual faces with different poses are synthesized based on the personalized 3D face to characterize the face subspace. Finally, face recognition is conducted based on these representative virtual faces. Compared with other related works, this framework has the following advantages: (1) only one single frontal face is required for face recognition, which avoids the burdensome enrollment work; and (2) the synthesized face samples provide the capability to conduct recognition under difficult conditions like complex pose, illumination and expression. From the experimental results, we conclude that the proposed method improves the accuracy of face recognition by varying the pose, illumination and expression.

• 出版日期2014-3