Robust Real-Time Face Detection Using Face Certainty Map

  • Bongjin Jun
  • Daijin Kim
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4642)


In this paper, we present a robust real-time face detection algorithm. We improved the conventional face detection algorithms for three different steps. For preprocessing step, we revise the modified census transform to compensate the sensitivity to the change of pixel values. For face detection step, we propose difference of pyramid(DoP) images for fast face detection. Finally, for postprocessing step, we propose face certainty map(FCM) which contains facial information such as facial size, location, rotation, and confidence value to reduce FAR(False Acceptance Rate) with constant detection performance. The experimental results show that the reduction of FAR is ten times better than existing cascade adaboost detector while keeping detection rate and detection time almost the same.


Face Image Face Detection False Acceptance Rate Pyramid Image Scanning Window 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Lee, H.-S., Kim, D.: Facial expression transformations for expression-invariant face recognition. In: Proc. of International Symposium on Visual Computing, pp. 323–333 (2006)Google Scholar
  2. 2.
    Sung, K.K.: Learning and Example Selection for Object and Pattern Recognition. PhD thesis, MIT, AI Lab, Cambridge (1996)Google Scholar
  3. 3.
    Viola, P., Jones, M.: Fast and Robust Classification using Asymmetric Adaboost and a Detector Cascade. In: Advances in Neural Information Processing System, vol. 14, MIT Press, Cambridge (2002)Google Scholar
  4. 4.
    Froba, B., Ernst, A.: Face detection with the modified census transform. In: Sixth IEEE International Conference on Automatic Face and Gesture Recognition, IEEE Computer Society Press, Los Alamitos (2004)Google Scholar
  5. 5.
    Yang, J., Waibel, A.: A real-time face tracker. In: Proc. 3rd Workshop on Appl. of Computer Vision, pp. 142–147 (1996)Google Scholar
  6. 6.
    Dai, Y., Nakano, Y.: Face texture model based on sgld and its application in face detection in a color scene. Pattern Recognition 29, 1007–1017 (1996)CrossRefGoogle Scholar
  7. 7.
    Osuna, E.: Support Vector Machines: Training and Applications. PhD thesis, MIT, EE/CS Dept., Cambridge (1998)Google Scholar
  8. 8.
    Mohan, A., Papageorgiou, C., Poggio, T.: Examplebased object detection in images by components. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 349–361 (2001)CrossRefGoogle Scholar
  9. 9.
    Sung, K.K., Poggio, T.: Example-based learning for view-based human face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 39–51 (1998)CrossRefGoogle Scholar
  10. 10.
    Schneiderman, H., Kanade, T.: A statistical method for 3d object detection applied to face and cars. In: Computer Vision and Pattern Recognition, pp. 746–751 (2000)Google Scholar
  11. 11.
    Rowley, H., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 23–38 (1998)CrossRefGoogle Scholar
  12. 12.
    Zabih, R., Woodfill, J.: A non-parametric approach to visual correspondence. IEEE Transactions on Pattern Analysis and Machine Intelligence (1996)Google Scholar
  13. 13.
    Kim, H.C., Sung, J.W., Je, H.M., Kim, S.K., Jun, B.J., Kim, D., Bang, S.Y.: Asian Face Image Database PF01. Technical Report, Intelligent Multimedia Lab, Dept. of CSE, POSTECH (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Bongjin Jun
    • 1
  • Daijin Kim
    • 1
  1. 1.Department of Computer Science and Engineering, Pohang University of Science and Technology 

Personalised recommendations