We present a method for automatically learning discriminative image patches for the recognition of given object classes. The approach applies discriminative training of log-linear models to image patch histograms. We show that it works well on three tasks and performs significantly better than other methods using the same features. For example, the method decides that patches containing an eye are most important for distinguishing face from background images. The recognition performance is very competitive with error rates presented in other publications. In particular, a new best error rate for the Caltech motorbikes data of 1.5% is achieved.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Discriminative training for object recognition using image patches


    Contributors:
    Deselaers, T. (author) / Keysers, D. (author) / Ney, H. (author)


    Publication date :

    2005-01-01


    Size :

    514287 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Object recognition using discriminative parts

    Liu, Y. H. / Lee, A. J. / Chang, F. | British Library Online Contents | 2012


    Learning Discriminative Canonical Correlations for Object Recognition with Image Sets

    Kim, T.-K. / Kittler, J. / Cipolla, R. | British Library Conference Proceedings | 2006




    Discriminative Training for HMM-Based Offline Handwritten Character Recognition

    Nopsuwanchai, R. / Povey, D. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2003