Paper
30 September 2011 Pupil detection in video images
Amir Liaghatdar, Kaveh Kangarloo, Fardad Farokhi
Author Affiliations +
Proceedings Volume 8285, International Conference on Graphic and Image Processing (ICGIP 2011); 82850B (2011) https://doi.org/10.1117/12.913089
Event: 2011 International Conference on Graphic and Image Processing, 2011, Cairo, Egypt
Abstract
Video based pupil detection techniques are useful for Perceptual user interfaces and human monitoring. Pupil detection plays a vital role in identification systems. This paper presents an algorithm for pupil detection in video images under active infrared (IR) illumination. At first, using a low pass filter the eyelashes are removed. Following, the thresholding process takes place. Using the Otsu's thresholding method, the proper thresholding value is estimated. Then, using the genetic algorithm, filter band width and threshold value are estimated accurately. After the pupil segmentation process, pupil boundary is modelled. The modeling process is based on circular Hough transform. Experimental results show promising performances on eye video images captured in ideal and non-ideal conditions.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Amir Liaghatdar, Kaveh Kangarloo, and Fardad Farokhi "Pupil detection in video images", Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 82850B (30 September 2011); https://doi.org/10.1117/12.913089
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Eye models

Video

Image segmentation

Hough transforms

Genetic algorithms

Eye

Infrared imaging

Back to Top