Finding faces in photographs
Authors:
- K.S. KumarKKK.S. Kumar
- J. KarlekarJKJ. Karlekar
- R. ManivasakanRMR. Manivasakan
- M.M. PatilMPM.M. Patil
- U.B. DesaiUDU.B. Desai
- P.G. PoonachaPPP.G. Poonacha
- S. ChaudhuriSCS. Chaudhuri
- 1 January 1998
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 640-645
Abstract
Two new schemes are presented for finding human faces in a photograph. The first scheme approximates the unknown distributions of the face and the face-like manifolds wing higher order statistics (HOS). An HOS-based data clustering algorithm is also proposed. In the second scheme, the face to non-face and non-face to face transitions are learnt using a hidden Markov model (HMM). The HMM parameters are estimated corresponding to a given photograph and the faces are located by examining the optimal state sequence of the HMM. Experimental results are presented on the performance of both the schemes.Keywords
This publication has 6 references indexed in Scilit:
- Locating human faces in photographsInternational Journal of Computer Vision, 1996
- Neural network-based face detection1996
- HMM-based architecture for face identificationImage and Vision Computing, 1994
- Using local orientation and hierarchical spatial feature matching for the robust recognition of objects1991
- An introduction to hidden Markov modelsIEEE ASSP Magazine, 1986
- The viterbi algorithmProceedings of the IEEE, 1973