Abstract
Locating the center of the eyes plays a significant role in many computer vision applications and research, such as face alignment, face recognition, human-computer interaction, control devices for disabled people, user attention and gaze estimation. The disturbances such as occlusions by eyelashes or eyelids, uneven spots and spectacle frames of glasses affect the accuracy and stability of eye center location. This paper presents a hybrid eye center locating methodology for infrared eye images. The pupil edge points are extracted by Starburst algorithm, and when we get the position and the gradient of the edge points, the approximate pupil boundary is determined by a convex region voting methods. After that, the boundary edge points are iteratively optimized by fitting an ellipses modeling constraint. Finally, the pupil is located correctly. Experiment shows that this algorithm has performance advantages compared with some state of the art approaches in pupil localization accuracy, iteration times and their performance. This algorithm combining convex area voting and model constraint has strong robustness, high accuracy and speed in real environments with occlusions and distortion pupil.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
C. Jin and Y. Li, “Estimation method of the fixation point in gaze tracking system,” Sci. Technol. Eng. 16 (13), 201–205 (2016).
Y. Zhao, X. Nie, and J. Luo, “Pupil center location based on radial symmetry combined with selective threshold,” J. Optoelectron.·Laser. 27 (11), 1208–1213 (2016).
S. Mao, “Exact pupil detection algorithm combining Hough transformation and contour maching,” J. Comput. Appl. 36 (5), 1415–1420 (2016).
S. Y. Gwon, C. W. Cho, H. C. Lee, W. O. Lee, and K. R. Park, “Robust eye and pupil detection method for gaze tracking,” Int. J. Adv. Robotic Syst. 10, 1–7 (2013).
R. Valenti and T. Gevers, “Accurate eye center location through invariant isocentric patterns,” IEEE Trans. Pattern Anal. Mach. Intell. 34 (9), 1785–1798 (2012).
Z. Wang, H. Chen, and B. Chen, “Pupil positioning approach under low contrast blurred environment,” Comput. Eng. Appl. 52 (12), 205–209 (2016).
X. Hu and Z. Wang, “Fast eye center and corner location by gradient feature reconstruction,” J. Comput.-Aided Design Comput. Graph. 27 (12), 2256–2263 (2015).
J. Daugman, “New methods in iris recognition,” IEEE Trans. Syst. Man. Cybern. B. Cybern. 37 (5), 1167–1175 (2007).
D. Li and D. Winfield, “Starburst: a hybrid algorithm for video-based eye tracking combining feature-based and model-based approaches,” in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (San Diego, 2005), pp. 79–87.
C. Colombo, D. Comanducci, and A. Del Bimbo, “Robust tracking and remapping of eye appearance with passive computer vision,” ACM Trans. Multimed. Comput. Commun. Appl. 3 (4), 1–20 (2007).
R. Halir and J. Flusser, “Numerically stable direct least squares fitting of ellipses,” in Proc. 6th Int. Conf. in Central Europe on Computer Graphics and Visualization (Plzen, 1998), pp. 59–108.
J. Daugman, “How iris recognition works,” IEEE Trans. Circuits Syst. Video Technol. 14 (1), 33–36 (2004).
M. Paramanandam, et al., “Boundary extraction for imperfectly segmented nuclei in breast histopathology images–a convex edge grouping approach,” in Proc. Int. Workshop on Combinatorial Image Analysis (Springer Int. Publ., 2014).
F. Timm and E. Barth, “Accurate eye center localisation by means of gradients,” in Proc. 6th Int. Conf. on Computer Vision Theory and Applications VISAPP 2011 (Vilamoura, March 5–7, 2011), pp. 125–130.
R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision (Cambridge Univ. Press, 2003).
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Yuanhui Zhang was born in 1982. He is now working at China Jiliang university as an associate professor. He is also a deputy director of department of Mechanical Engineering. He obtained the bachelor degree from Zhejiang University in 2004. And he got his doctor degree in Zhejiang University in 2011. His research interests include computer vision and robotics. He has had 8 papers published.
Yan Li was born in 1993. She is studying for a master’s degree at China Jiliang University and she received the bachelor’s degree at the same university in 2015. Her research interests include computer vision and image processing.
Bo Xie was born in 1988. He received the bachelor’s degree at Shenyang Aeronautics Industrial College in 2013 and received the master’s degree at China Jiliang University in 2016. Now his research field is pattern recognition and image processing.
Xiaolu Li was born in 1968. He received the bachelor’s degree in engineering in 1991 at Shenyang Aeronautics Industrial College and received the master’s degree in engineering in 1996 at Zhejiang University. He got his Ph.D. degree in 2005 at Shanghai Jiaotong University. Now he is working at College of Electrical and Mechanical Engineering of China Jiliang University in Hangzhou. His research field is mechatronics design and system simulation and has now had 85 scientific publications.
Jun Jiang Zhu was born in 1987. He is now working at China Jiliang university as a lecturer. He obtained the bachelor degree from Zhengzhou University in 2009. And he got his master degree and doctor degree in Hua Zhong University of Science and Technology in China in 2011 and 2015 respectively. Now his research field is signal processing. He has now had 8 papers published, two of which are indexed by SCI.
Rights and permissions
About this article
Cite this article
Zhang, Y., Li, Y., Xie, B. et al. Pupil localization algorithm combining convex area voting and model constraint. Pattern Recognit. Image Anal. 27, 846–854 (2017). https://doi.org/10.1134/S1054661817040216
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661817040216