A fast simulated annealing algorithm is developed for automatic object recognition. The normalized correlation coefficient is used as a measure of the match between a hypothesized object and an image. Templates are generated on-line during the search by transforming model images. Simulated annealing reduces the search time by orders of magnitude with respect to an exhaustive search. The algorithm is applied to the problem of how landmarks, for example, traffic signs, can be recognized by an autonomous vehicle or a navigating robot. The algorithm works well in noisy, real-world images of complicated scenes for model images with high information content.


    Access

    Download


    Export, share and cite



    Title :

    Fast Object Recognition in Noisy Images Using Simulated Annealing


    Contributors:

    Publication date :

    1995


    Size :

    9 pages , 1311904 byte , 735998 byte


    Type of media :

    Miscellaneous


    Type of material :

    Electronic Resource


    Language :

    English




    Fast Object Recognition in Noisy Images Using Simulated Annealing

    Betke, M. / Makris, N. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995


    Fast Lexicon-Based Word Recognition in Noisy Index Card Images

    Lucas, S. / Patoulas, G. / Downton, A. et al. | British Library Conference Proceedings | 2003


    Fast lexicon-based word recognition in noisy index card images

    Lucas, S.M. / Patoulas, G. / Downton, A.C. | IEEE | 2003


    Object Manipulation With Dextrous Robotic Hand Using Simulated Annealing

    Vass, Gábor / Payandeh, Shahram / Lantos, Béla | BASE | 1999

    Free access

    Elliptical Object Detection in Noisy Images Using a Multiresolution Structure

    Lee, C. K. / Lee, K. W. / Li, K. C. | British Library Conference Proceedings | 1993