Standard but ad hoc measures such as sum-of-squared pixel differences (SSD) are often used when comparing and registering two images that have not been previously observed before. In this paper, we propose a framework to address the problem of learning a parametric feature distance measure to measure the dissimilarity between pairs of images. The method is based on optimizing the parameters of the distance measure in order to minimize correspondence classification errors on training data. Because the learning process involves relative (rather than absolute) visual content between image pairs, the learned distance measure may also be applied to other images with very different visual content. Results on matching classification with a wide variety of image content show that the learned feature distance measure clearly outperforms the standard measures of SSD, chamfer and Bhattacharyya histogram distances.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning feature distance measures for image correspondences


    Contributors:
    Chen, X. (author) / Cham, T.-J. (author)


    Publication date :

    2005-01-01


    Size :

    395681 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Unsupervised Feature Learning for Dense Correspondences Across Scenes

    Zhang, C. / Shen, C. / Shen, T. | British Library Online Contents | 2016



    Coding of Image Feature Descriptors for Distributed Rate-efficient Visual Correspondences

    Yeo, C. / Ahammad, P. / Ramchandran, K. | British Library Online Contents | 2011


    Visual Servoing without Feature Correspondences Using Eigenspace Method

    Noguchi, T. / Deguchi, K. | British Library Online Contents | 1996