A Facial Features Matching Method with Age Robustness Based on SIFT Algorithm

Facial change with age is always a problem in facial features matching for photos of ID cards. In order to solve this problem, a novel facial features matching method based on SIFT algorithm is proposed. Inspired by attention mechanism of the visual system, the facial features focuses on the four sub regions (left eye, right eye, nose and mouth), ignoring other unimportant regions, and different weights are used to each region according to the contribution of each region to matching accuracy. The experimental results show that the proposed method can effectively reduce the influence that age change lead to a sharp decline in matching accuracy, and this algorithm can significantly reduce the time of features matching.

[1]  Shiguang Shan,et al.  Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment , 2014, ECCV.

[2]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[3]  Timothy F. Cootes,et al.  Interpreting face images using active appearance models , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[4]  Qingxiang Wu,et al.  A visual attention model based on hierarchical spiking neural networks , 2013, Neurocomputing.

[5]  Chen Zhi-gang.  A Mixed Face Recognition Method Based on ID Card , 2003 .

[6]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[7]  Xinggang Lin,et al.  Face recognition across different poses using a single 2D model view , 2003, IEEE International Conference on Robotics, Intelligent Systems and Signal Processing, 2003. Proceedings. 2003.

[8]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.