Eyelash detection model for accurate iris segmentation

 In this paper, we present a novel eyelash detection model based on three criterions: 1) separable eyelash condition, 2) non-informative condition and 3) connective criterion. The first condition handles separable eyelash and the second condition manages multiple eyelashes. The last criterion avoids misclassification of strong iris texture as a single and separable eyelash. A number of images are selected to evaluate the accuracy and necessity of the eyelash detection model. The results are encouraging.

[1]  Hanqi Zhuang,et al.  Real-time eye feature tracking from a video image sequence using Kalman filter , 1994, Conference Record Southcon.

[2]  Lijun Yin,et al.  Eye tracking and animation for MPEG-4 coding , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[3]  Hanqi Zhuang,et al.  A cascaded scheme for eye tracking and head movement compensation , 1998, IEEE Trans. Syst. Man Cybern. Part A.

[4]  D. H. Mellor,et al.  Real time , 1981 .