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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Finding faces in photographs


    Contributors:


    Publication date :

    1998-01-01


    Size :

    1217386 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Finding Faces in Photographs

    Rajagopalan, A. N. / Sunil Kumar, K. / Karlekar, J. et al. | British Library Conference Proceedings | 1998


    Locating Human Faces in Photographs

    Govindaraju, V. | British Library Online Contents | 1996


    Locating human faces in newspaper photographs

    Govindaraju, V. / Sher, D.B. / Srihari, R.K. et al. | IEEE | 1989


    Finding Faces in Color Images using Wavelet Transform

    Karlekar, J. / Desai, U. / IEEE | British Library Conference Proceedings | 1999


    Finding faces in color images using wavelet transform

    Karlekar, J. / Desai, U.B. | IEEE | 1999