We propose a method of face recognition that can consistently identify every face angle, assuming it is used in open spaces such as a normal room. We obtain the learning images not from an ideal world but from the real world, where users can move around freely with no constraints. We then automatically classify the face images that vary according to the user's position and posture by self-organization (unsupervised learning), and create a discrimination circuit using only the best face images for the recognition task. We show that the recognition rate for images with various facial angles in the real world can be improved by automatic classification through self-organization.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Automatic face classifications by self-organization for face recognition


    Contributors:
    Sato, Y. (author) / Yoda, I. (author) / Sakaue, K. (author)


    Publication date :

    2003-01-01


    Size :

    533530 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Automatic Face Classifications by Self-Organization for Face Recognition

    Sato, Y. / Yoda, I. / Sakaue, K. et al. | British Library Conference Proceedings | 2003


    Automatic Seat Adjustment using Face Recognition

    Vamsi, Malneedi / Soman, K.P. / Guruvayurappan, K. | IEEE | 2020


    Automatic face authentication with self compensation

    Lin, T. H. / Shih, W. P. | British Library Online Contents | 2008


    Learning and Caricaturing the Face Space Using Self-Organization and Hebbian Learning for Face Processing

    Pujol, A. / Wechsler, H. / Villanueva, J. et al. | British Library Conference Proceedings | 2001


    Best of Automatic Face and Gesture Recognition 2011

    Stiefelhagen, R. / Bartlett, M. S. / Bowyer, K. | British Library Online Contents | 2012