Appearance-based object recognition systems rely on training from imagery, which allows the recognition of objects without requiting a 3D geometric model. It has been little explored whether such systems can be trained from imagery that is unlabeled, and whether they can be trained from imagery that is not trivially segmentable. In this paper we present a method for minimally supervised training of a previously developed recognition system from unlabeled and unsegmented imagery. We show that the system can successfully extend an object representation extracted from one black background image to contain object features extracted from unlabeled cluttered images and can use the extended representation to improve recognition performance on a test set.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Minimally supervised acquisition of 3D recognition models from cluttered images


    Contributors:
    Selinger, A. (author) / Nelson, R.C. (author)


    Publication date :

    2001-01-01


    Size :

    919639 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Minimally Supervised Acquisition of 3D Recognition Models from Cluttered Images

    Selinger, A. / Nelson, R. C. / IEEE | British Library Conference Proceedings | 2001


    Robustness of model-based recognition in cluttered images

    Vergnet, R.L. / Saint-Marc, P. / Ayache, N. | IEEE | 1993


    Tracking in cluttered images

    Strens, M. J. / Gregory, I. N. | British Library Online Contents | 2003


    CAD-Based Vision: Object Recognition in Cluttered Range Images Using Recognition Strategies

    Arman, F. / Aggarwal, J. K. | British Library Online Contents | 1993


    A Local Basis Representation for Estimating Human Pose from Cluttered Images

    Agarwal, A. / Triggs, B. | British Library Conference Proceedings | 2006