Machine Vision and Applications

, Volume 21, Issue 5, pp 779–787

A fast connected components labeling algorithm and its application to real-time pupil detection

Short Paper

DOI: 10.1007/s00138-009-0183-1

Cite this article as:
Gabbur, P., Hua, H. & Barnard, K. Machine Vision and Applications (2010) 21: 779. doi:10.1007/s00138-009-0183-1

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 Segmentation 

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  1. 1.3DVIS Lab, College of Optical SciencesUniversity of ArizonaTucsonUSA
  2. 2.Department of Computer ScienceUniversity of ArizonaTucsonUSA