Maximum Likelihood Estimates for Object Detection Using Multiple Detectors

  • Magnus Oskarsson
  • Kalle Åström
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4109)


Object detection in real images has attracted much attention during the last decade. Using machine learning and large databases it is possible to develop detectors for visual categories that have a very high hit-rate, with low false positive rates. In this paper we investigate a general probabilistic framework for context based scene interpretation using multiple detectors. Methods for finding maximum likelihood estimates of scenes given detection results are presented. Although we have investigated how the method works for a specific case, namely for face detection, it is a general method. We show how to combine the results of a number of detectors i.e. face, eye, nose and mouth detectors. The methods have been tested using detectors trained on real images, with promising results.


Maximum Likelihood Estimate Object Detection Detection Result Face Detection Multiple Detector 
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.
    Crandall, D., Felzenszwalb, P., Huttenlocher, D.: Spatial priors for part-based recognition using statistical models. In: Proc. Conf. Computer Vision and Pattern Recognition, San Diego, USA, pp. I: 10–17 (2005)Google Scholar
  2. 2.
    Dryden, I.L., Mardia, K.V., Walder, A.N.: Review of the use of context in statistical image analysis. J. of Applied Statistics 24(5), 513–538 (1997)CrossRefGoogle Scholar
  3. 3.
    Forsyth, D., Fleck, M.: Body plans. In: CVPR, Puerto Rico, USA, pp. 678–683 (1997)Google Scholar
  4. 4.
    Kruppa, H., Schiele, B.: Using local context to improve face detection. In: BMVC, Norwich, England, pp. 3–12 (2003)Google Scholar
  5. 5.
    Mikolajczyk, C., Schmid, K., Zisserman, A.: Human Detection Based on a Probabilistic Assembly of Robust Part Detectors. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 69–82. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  6. 6.
    Mohan, A., Papageorgiou, C., Poggio, T.: Example-based object detection in images by components. IEEE Trans. Pattern Analysis and Machine Intelligence 23(4), 349–361 (2001)CrossRefGoogle Scholar
  7. 7.
    Prince, S.J.D., Elder, J.H., Hou, Y., Sizintsev, M., Olevskiy, Y.: Statistical cue integration for foveated wide-field surveillance. In: Proc. Conf. Computer Vision and Pattern Recognition, San Diego, USA, pp. II: 603–610 (2005)Google Scholar
  8. 8.
    Schneiderman, H.: Learning Statistical Structure for Object Detection. In: Petkov, N., Westenberg, M.A. (eds.) CAIP 2003. LNCS, vol. 2756, pp. 434–441. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  9. 9.
    Schneiderman, H., Kanade, T.: Object detection using the statistics of parts. Int. Journal of Computer Vision 56(3), 151–177 (2004)CrossRefGoogle Scholar
  10. 10.
    Sidenbladh, H., Black, M.: Learning image statistics for bayesian tracking. In: ICCV, vancouver, canada, pp. 709–716 (2001)Google Scholar
  11. 11.
    Torralba, A.: Contextual priming for object detection. Int. Journal of Computer Vision 53(2), 169–191 (2003)CrossRefGoogle Scholar
  12. 12.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. Conf. Computer Vision and Pattern Recognition. IEEE Computer Society Press, Los Alamitos (2001)Google Scholar
  13. 13.
    Yang, M.H., Kriegman, D.J., Ahuja, N.: Detecting faces in images: A survey. IEEE Trans. Pattern Analysis and Machine Intelligence 24(1), 34–58 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Magnus Oskarsson
    • 1
  • Kalle Åström
    • 1
  1. 1.Centre For Mathematical SciencesLund UniversityLundSweden

Personalised recommendations