A fast and accurate eyelids and eyelashes detection approach for iris segmentation

Iris segmentation step is an essential process in iris recognition system. This step becomes much more difficult due to the presence of eyelids and eyelashes. This paper contributes to fast and robust eyelids and eyelash detection algorithm. The main contributions are: (1) Proposition of robust eyelids detection algorithm based on the Radon transform and polynomial curve fitting, using Least Squares Fitting method. (2) Eyelashes detection using diagonal gradient and thresholding process. The proposed method was evaluated on the CASIA V3 database and compared to the previous work. As the experimental results show that the proposed algorithm provides an encouraging performance in terms of accuracy and computational complexity. Moreover our method is very useful for iris recognition system which requires excluding the bits generated from eyelashes regions during iris matching stage.