Finding faces in photographs

Authors:
  • KKK.S. Kumar
    K.S. Kumar
  • JKJ. Karlekar
    J. Karlekar
  • RMR. Manivasakan
    R. Manivasakan
  • MPM.M. Patil
    M.M. Patil
  • UDU.B. Desai
    U.B. Desai
  • PPP.G. Poonacha
    P.G. Poonacha
  • SCS. Chaudhuri
    S. Chaudhuri

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.

This publication has 6 references indexed in Scilit: