Title :
Precise eye localization with improved SDM
Author :
Mingcai Zhou;Xiying Wang;Haitao Wang;Jingu Heo;DongKyung Nam
Author_Institution :
Samsung Research Center-Beijing, SAIT China Lab Beijing, China
Abstract :
In this paper, we propose a precise and fast eye center localization method. The method is based on SDM [1] algorithm, which has achieved impressive performance in face alignment area. In this work, we further improve the basic SDM algorithm in two aspects: 1) employ the coarse to fine strategy to enhance the robustness to initialization; 2) utilize multiple nonlinear features to ensure the robustness while improve the accuracy. Experimental results on BioID database shows that our improved SDM achieves preferable localization accuracy against the state-of-the-art methods at a speed as fast as 2ms to locate two eyes.
Keywords :
"Shape","Feature extraction","Databases","Training","Face","Robustness","Lighting"
Conference_Titel :
Image Processing (ICIP), 2015 IEEE International Conference on
DOI :
10.1109/ICIP.2015.7351651