We address the problem of finding point correspondences in images by way of an approach to template matching that is robust under affine distortions. This is achieved by applying "geometric blur" to both the template and the image, resulting in a fall-off in similarity that is close to linear in the norm of the distortion between the template and the image. Results in wide baseline stereo correspondence, face detection, and feature correspondence are included.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Geometric blur for template matching


    Beteiligte:
    Berg, A.C. (Autor:in) / Malik, J. (Autor:in)


    Erscheinungsdatum :

    2001-01-01


    Format / Umfang :

    1115919 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Geometric Blur and Template Matching

    Berg, A. C. / Malik, J. / IEEE | British Library Conference Proceedings | 2001


    Pattern matching using the blur hit-miss transform

    Bloomberg, D. S. / Vincent, L. | British Library Online Contents | 2000



    Real-Time Geometric Motion Blur for a Deforming Polygonal Mesh

    Jones, N. / Keyser, J. / IEEE | British Library Conference Proceedings | 2005