Efficient iris segmentation method in unconstrained environments

作者：

Highlights：

• An efficient method is proposed for noisy iris image segmentation.

• K-means is used to determine the expected region of iris.

• Circular Hough Transform is used to localize the iris and pupil.

• Three methods to reduce the execution time of Circular Hough Transform are used.

• A new algorithm is proposed to handle upper eyelid obstructions.

摘要

•An efficient method is proposed for noisy iris image segmentation.•K-means is used to determine the expected region of iris.•Circular Hough Transform is used to localize the iris and pupil.•Three methods to reduce the execution time of Circular Hough Transform are used.•A new algorithm is proposed to handle upper eyelid obstructions.

论文关键词：Biometrics,Iris recognition,Iris segmentation,Non-cooperative iris recognition,Eyelid localization

论文评审过程：Received 16 July 2012, Revised 31 March 2013, Accepted 2 June 2013, Available online 15 June 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.06.004