A fast connected components labeling algorithm and its application to real-time pupil detection
Short Paper
First Online:
Received:
Revised:
Accepted:
- 330 Downloads
- 3 Citations
Abstract
We describe a fast connected components labeling algorithm using a region coloring approach. It computes region attributes such as size, moments, and bounding boxes in a single pass through the image. Working in the context of real-time pupil detection for an eye tracking system, we compare the time performance of our algorithm with a contour tracing-based labeling approach and a region coloring method developed for a hardware eye detection system. We find that region attribute extraction performance exceeds that of these comparison methods. Further, labeling each pixel, which requires a second pass through the image, has comparable performance.
Keywords
Connected components labeling Pupil detection Eye tracking Region coloring SegmentationPreview
Unable to display preview. Download preview PDF.
References
- 1.
- 2.Amir A., Zimet L., Sangiovanni-Vincentelli A., Kao S.: An embedded system for an eye-detection sensor. Comput. Vis. Image Underst. 98(1), 104–123 (2005)CrossRefGoogle Scholar
- 3.Ballard D.H., Brown C.M.: Computer Vision. Prentice Hall, NJ (1982)Google Scholar
- 4.Chang F., Chen C.J., Lu C.J.: A linear-time component-labeling algorithm using contour tracing technique. Comput. Vis. Image Underst. 93(2), 206–220 (2004)CrossRefGoogle Scholar
- 5.Dillencourt M.B., Samet H., Tamminen M.: A general approach to connected-component labeling for arbitrary image representations. J. ACM 39(2), 253–280 (1992)MATHCrossRefMathSciNetGoogle Scholar
- 6.Doyle J., Rivest R.L.: Linear expected time of a simple union-find algorithm. Inf. Proc. Lett. 5(5), 146–148 (1976)MATHCrossRefMathSciNetGoogle Scholar
- 7.Duchowski A.T.: Eye Tracking Methodology: Theory and Practice. Springer, New York (2001)Google Scholar
- 8.Ebisawa Y.: Improved video-based eye-gaze detection method. IEEE Trans. Inst. Meas. 47(4), 948–955 (1998)CrossRefGoogle Scholar
- 9.Haralick R.M.: Real-Time Parallel Computing Image Analysis, chap. Some Neighborhood Operators, pp. 11–35. Plenum Press, New York (1981)Google Scholar
- 10.Hua H., Krishnaswamy P., Rolland J.P.: Video-based eyetracking methods and algorithms in head-mounted displays. Opt. Express 14(10), 4328–4350 (2006)CrossRefGoogle Scholar
- 11.Hua H., Pansing C., Rolland J.P.: Modeling of an eye-imaging system for optimizing illumination schemes in an eye-tracked head-mounted display. Appl. Opt. 46(32), 1–14 (2007)Google Scholar
- 12.Hutchinson T.E., White K.P., Martin W.N., Reichert K.C., Frey L.A.: Human–computer interaction using eye-gaze input. IEEE Trans. Syst. Man. Cybern. 19(6), 1527–1534 (1989)CrossRefGoogle Scholar
- 13.Kapoor, A., Picard, R.W.: A real-time head nod and shake detector. In: PUI ’01: Proceedings of the 2001 Workshop on Perceptive User interfaces, pp. 1–5 (2001)Google Scholar
- 14.Lumia R., Shapiro L., Zuniga O.A.: A new connected components algorithm for virtual memory computers. Comput. Vis. Graph. Image Proc. 22(2), 287–300 (1983)CrossRefGoogle Scholar
- 15.Morimoto C., Koons D., Amir A., Flickner M.: Pupil detection and tracking using multiple light sources. Image Vis. Comput. 18(4), 331–335 (2000)CrossRefGoogle Scholar
- 16.Rosenfeld A., Pfaltz J.L.: Sequential operations in digital picture processing. J. ACM 13(4), 471–494 (1966)MATHCrossRefGoogle Scholar
- 17.Samal A., Iyengar P.A.: Automatic recognition and analysis of human faces and facial expressions: a survey. Pattern Recogn. 25(1), 65–77 (1992)CrossRefGoogle Scholar
- 18.Schwiegerling J.: Field Guide to Visual and Ophthalmic Optics. SPIE Press, Bellingham (2004)CrossRefGoogle Scholar
- 19.di Stefano, L., Bulgarelli, A.: A simple and efficient connected components labeling algorithm. In: Proc. 10th Intl. Conf. Image Anal. Proc., pp. 322–327 (1999)Google Scholar
- 20.Suzuki, K., Horiba, I., Sugie, N.: Fast connected-component labeling based on sequential local operations in the course of forward raster scan followed by backward raster scan. In: IEEE Intl. Conf. Pattern Recog., vol. 2, pp. 434–437 (2000)Google Scholar
- 21.Suzuki K., Horiba I., Sugie N.: Linear-time connected-component labeling based on sequential local operations. Comput. Vis. Image Underst. 89(1), 1–23 (2003)MATHCrossRefGoogle Scholar
- 22.Tarjan R.E.: Efficiency of a good but not linear set union algorithm. J. ACM 22(2), 215–225 (1975)MATHCrossRefMathSciNetGoogle Scholar
- 23.Wu, K., Otoo, E., Suzuki, K.: Two strategies to speed up connected component labeling algorithms. Tech. Rep. 59102, Lawrence Berkeley National Lab (2005)Google Scholar
- 24.Zhao, S., Grigat, R.R.: Robust eye detection under active infrared illumination. In: IEEE Intl. Conf. Pattern Recogn., pp. 481–484 (2006)Google Scholar
- 25.Zhu D., Moore S.T., Raphan T.: Robust pupil center detection using a curvature algorithm. Comput. Methods Programs Biomed. 59(3), 145–157 (1999)CrossRefGoogle Scholar
Copyright information
© Springer-Verlag 2009