FACIAL POSE ESTIMATION FOR IMAGE RETRIEVAL

Andreas Savakis, James Schimmel

2007

Abstract

Face detection is a prominent semantic feature which, along with low-level features, is often used for content-based image retrieval. In this paper we present a human facial pose estimation method that can be used to generate additional metadata for more effective image retrieval when a face is already detected. Our computationally efficient pose estimation approach is based on a simplified geometric head model and combines artificial neural network (ANN) detectors with template matching. Testing at various poses demonstrated that the proposed method achieves pose estimation within 4.28 degrees on average, when the facial features are accurately detected.

References

  1. Burl M.C., and Perona P., 1996. Recognition of Planar Object Classes. In IEEE Conference on Computer Vision and Patten Recognition.
  2. Choi K. N., Carcassoni M., and Hancock. E., 1998. Estimating 3D Facial Pose using the EM Algorithm. In 9th British Machine Vision Conference.
  3. Fergus R, Perona P., and Zisserman A., 2003. Object Class Recognition by Unsupervised ScaleInvariant Learning. In IEEE Conference on Computer Vision and Pattern Recognition.
  4. Rowley H. A., Baluja S., and Kanade T., 1998. Neural Network-Based Face Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, pp. 23-38.
  5. Haddadnia J., Faez K., and Ahmadi M., 2002. N-Feature Neural Network Human Face Recognition. In 15th international Conference on Vision Interface.
  6. Yilmaz A. and Shah M., 2002. Automatic Feature Detection and Pose Recovery for Faces. In 5th Asian Conference on Computer Vision.
  7. Storring M., Andersen H. J. and Granum E., 1999. Skin Colour detection under changing lighting conditions. In 7th symposium on Intelligent Robotics Systems.
  8. Gong S., Mckenna S. J., and Psarrou A,, 2000. Dynamic Vision. Imperial Collage Press, London.
  9. Fitzpatrick P., 2003. Head Pose estimation without manual initialization. Massachusetts Institute of Technology. AI Lab Technical Report.
  10. Farber A., 2003. Introduction to SSE Programming. http://www.codeproject.com/cpp/sseintro.asp. The Code Project.
Download


Paper Citation


in Harvard Style

Savakis A. and Schimmel J. (2007). FACIAL POSE ESTIMATION FOR IMAGE RETRIEVAL . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 978-972-8865-74-0, pages 173-177. DOI: 10.5220/0002061201730177


in Bibtex Style

@conference{visapp07,
author={Andreas Savakis and James Schimmel},
title={FACIAL POSE ESTIMATION FOR IMAGE RETRIEVAL},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2007},
pages={173-177},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002061201730177},
isbn={978-972-8865-74-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - FACIAL POSE ESTIMATION FOR IMAGE RETRIEVAL
SN - 978-972-8865-74-0
AU - Savakis A.
AU - Schimmel J.
PY - 2007
SP - 173
EP - 177
DO - 10.5220/0002061201730177