A New Method of the Accurate Eye Corner Location

  • Yong Yang
  • Yunxia Lu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7413)


Eye corner location is a hot research topic in recent years. A novel eye corner Location method is proposed in the paper. Firstly, a haar features face detection based on adaboost is used to detect the face in an image. Secondly, a step of accurate eye corner location is proposed, which consists of rough eye location, contour extraction ellipse fitting, corner detection and eye corner location. Rough eye location is used for reducing the search range in the image. Then contour extraction based on ellipse fitting is taken. In the following, the curvature scale space(CSS) corner detection operator is used for corners detection. At last, the inner and outer eye corners can be determined according to statistics result of frequency distribution of the corner points projection. The proposed method is proved to be an effective and robust method according to the result of comparative experiments.


contour extraction ellipse fitting corner detection eye corner location 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Moein, L., AmirMohamad, S.Y.: Corner Sharpening with Modified Harris Corner Detection to Localize Eyes in Facial Images. In: IEEE International Conference on International Symposium ELMAR 2010, vol. 9, pp. 27–31 (2010)Google Scholar
  2. 2.
    Paul, V., Michael, J.: Robust Real-time Object Detection. International Journal of Computer Vision 57(2), 137–154 (2004)CrossRefGoogle Scholar
  3. 3.
    Lihui, C., Christos, G., Yang, M.Y.: Reduced Complexity Eye Detector for Colour Images using Harris Corners, Color Heuristics and Edge Maps. IEEE PRIME 11, 245–248 (2006)Google Scholar
  4. 4.
    Stylianos, A., Nikolaos, N., Ioannis, P.: Detection of Facial Characteristics based on Edge Information. In: Proceedings of VISAPP (2) 2007, pp. 247–252 (2007)Google Scholar
  5. 5.
    Zhihua, Z., Xin, G.: Projection Functions for Eye Detection. Pattern Recognition 37(5), 1–10 (2004)Google Scholar
  6. 6.
    Peng, W., Qiang, J.: Multi-View Face and Eye Detection Using Discriminant Features. Computer Vision and Image Understanding 105(2), 99–111 (2007)CrossRefGoogle Scholar
  7. 7.
    Song, J., Chi, Z.: A robust eye diction method using combined binary edge and intensity information. Pattern Recognition 39, 1110–1125 (2006)zbMATHCrossRefGoogle Scholar
  8. 8.
    Zhigang, Z., Mingquan, Z., Guohua, G.: Research on Automatic Localization of Facial Key Features. Computer Engineering and Applications 43(21), 197–198 (2007)Google Scholar
  9. 9.
    Cui, X., Ying, Z., Zengfu, W.: Semantic Feature Extraction for Accurate Eye Corner Detection. In: IEEE International Conference on Digital Object Identifier, pp. 1–4 (2008)Google Scholar
  10. 10.
    Rainer, L., Jochen, M.: An Extended Set of Haar-like Features for Rapid Object Detection. In: IEEE ICIP, pp. 900–903 (2002)Google Scholar
  11. 11.
    Zhengyou, Z.: Parameter Estimation Techniques: A Tutorial with Application to Conic Fitting. INRIA 10(2676), 59–76 (1995)Google Scholar
  12. 12.
    Xiaochen, H., Nelson, Y.: Corner Detector Based on Global and Local Curvature Properties. Optical Engineering 47(5), 057008-1–057008-12 (2007)Google Scholar
  13. 13.
    Jesorsky, O., Kirchberg, K.J., Frischholz, R.W.: Robust Face Detection Using the Hausdorff Distance. In: Bigun, J., Smeraldi, F. (eds.) AVBPA 2001. LNCS, vol. 2091, pp. 90–95. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  14. 14.
    Michael, L., Shigeru, A., Miyuki, K.: The Japanese Female Facial Expression (JAFFE) Database (1998),

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Yong Yang
    • 1
  • Yunxia Lu
    • 1
  1. 1.Institute of Computer Science & TechnologyChongqing University of Posts and TelecommunicationsChongqingP.R. China

Personalised recommendations