Relative Spatial Weighting of Features for Localizing Parts of Faces

  • Jacopo Bellati
  • Díbio Leandro Borges
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8259)


This paper proposes an approach for detecting important parts of faces in uncontrolled imaging settings. Regions of special interest in faces of humans are eyes and eyebrows, nose and mouth. The approach works by first extracting ORB (Oriented FAST and Rotated BRIEF) and SURF (Speeded up robust features) features, secondly a supervised learning step with a random subset of images is performed using k-means algorithm for devising the clusters’ centers of the important parts of faces. For the testing set of images the normalized values of each new ORB or SURF feature is weighted positively depending on its similarity and proximity of a cluster center (a face part). Tests were performed using the BioID dataset which consists of 1521 images of 23 different subjects in a variety of situations. Results show that the use of ORB features for face parts localization is more efficient and more precise than SIFT or SURF features alone. Also, the relative spatial weighting of a combination of ORB and SURF features enhances the localization of parts of faces.


Face parts localization ORB features face detection 


  1. 1.
    Bay, H., et al.: SURF: Speeded Up Robust Features. Computer Vision and Image Understanding (CVIU) 110(3), 346–359 (2008)CrossRefGoogle Scholar
  2. 2.
    Belhumeur, P., et al.: Localizing Parts of Faces Using a Consensus of Exemplars. In: Proceedings of IEEE CVPR 2011, pp. 545–552 (2011)Google Scholar
  3. 3.
    Bicego, M., et al.: On the use of SIFT features for face authentication. In: Proceedings of CVPRW 2006 (2006)Google Scholar
  4. 4.
    BioID Face Database, (visited in June 2013)
  5. 5.
    Chevallier, L., et al.: Facial Landmarks Localization Estimation by Cascaded Boosted Regression. In: Proceedings of VISAPP 2013 (2013)Google Scholar
  6. 6.
    Dantone, M., et al.: Real-time facial feature detection using conditional regression forests. In: Proceedings of IEEE CVPR 2012, pp. 2578–2585 (2012)Google Scholar
  7. 7.
    Ding, L., Martinez, A.M.: Features versus Context. IEEE Trans. PAMI 32(11), 2022–2038 (2010)CrossRefGoogle Scholar
  8. 8.
    Dreuw, P., et al.: SURF-Face: Face Recognition under Viewpoint Consistency Constraints. In: Proceedings of BMVC 2009 (2009)Google Scholar
  9. 9.
    Gourier, N., Hall, D., Crowley, J.: Facial Features Detection Robust to Pose, Illumination and Identity. In: Proceedings of IEEE SMC 2004, pp. 617–622 (2004)Google Scholar
  10. 10.
    Heinly, J., Dunn, E., Frahm, J.-M.: Comparative Evaluation of Binary Features. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 759–773. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    Klare, B., Jain, A.K.: On a taxonomy of facial features. In: Proceedings IEEE BTAS 2010, pp. 1–8 (2010)Google Scholar
  12. 12.
    Križaj, J., Štruc, V., Pavešić, N.: Adaptation of SIFT features for robust face recognition. In: Campilho, A., Kamel, M. (eds.) ICIAR 2010, Part I. LNCS, vol. 6111, pp. 394–404. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  13. 13.
    Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, vol 60(2), 91–110 (2004)CrossRefGoogle Scholar
  14. 14.
    Miksik, O., Mikolajczyk, K.: Evaluation of Local Detectors and Descriptors for Fast Feature Matching. In: Proceedings of ICPR 2012, pp. 2681–2684 (2012)Google Scholar
  15. 15.
    Rublee, E., et al.: ORB: an efficient alternative to SIFT or SURF. In: Proceedings of IEEE ICCV 2011, pp. 2564–2571 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Jacopo Bellati
    • 1
  • Díbio Leandro Borges
    • 1
  1. 1.Department of Computer ScienceUniversity of BrasiliaBrasíliaBrazil

Personalised recommendations