A central problem in object recognition is to determine the transformation that relates the model to the image, given some partial correspondence between the two. This is useful in determining whether an object is present in an image, and if so, in determining where the object is. We present a novel method of solving this problem that uses region information. In our approach, the model is divided into volumes and the image is divided into regions. Given a match between subsets of volumes and regions (without any explicit correspondence between different pieces of the regions), the alignment transformation is computed. The method applies to planar objects under similarity, affine and projective transformations and to projections of 3D objects undergoing affine and projective transformations.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Recognition using region correspondences


    Contributors:
    Basri, R. (author) / Jacobs, D. (author)


    Publication date :

    1995-01-01


    Size :

    917247 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Recognition Using Region Correspondences

    Basri, R. / Jacobs, D. W. | British Library Online Contents | 1997


    Recognition Using Region Correspondences

    Basri, R. / Jacobs, D. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995



    Using line correspondences in invariant signatures for curve recognition

    Holt, R. J. / Netravali, A. N. | British Library Online Contents | 1993


    CAMERA-RADAR FUSION USING CORRESPONDENCES

    MICHIELIN FRANCESCO / VOGEL OLIVER | European Patent Office | 2023

    Free access