eduzhai > Applied Sciences > Engineering >

Pupil Center Detection Approaches A comparative analysis

  • Save

... pages left unread,continue reading

Document pages: 15 pages

Abstract: In the last decade, the development of technologies and tools for eyetracking has been a constantly growing area. Detecting the center of the pupil,using image processing techniques, has been an essential step in this process.A large number of techniques have been proposed for pupil center detectionusing both traditional image processing and machine learning-based methods.Despite the large number of methods proposed, no comparative work on theirperformance was found, using the same images and performance metrics. In thiswork, we aim at comparing four of the most frequently cited traditional methodsfor pupil center detection in terms of accuracy, robustness, and computationalcost. These methods are based on the circular Hough transform, ellipse fitting,Daugman s integro-differential operator and radial symmetry transform. Thecomparative analysis was performed with 800 infrared images from theCASIA-IrisV3 and CASIA-IrisV4 databases containing various types ofdisturbances. The best performance was obtained by the method based on theradial symmetry transform with an accuracy and average robustness higher than94 . The shortest processing time, obtained with the ellipse fitting method,was 0.06 s.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...