Concavity detection using a binary mask-based approach
We present in this paper a study of concavity detection using binary edge mask information, and consistency links between them. A model for a corner is proposed as a particular arrangement of edge masks. In a second step, we merge these corner in order to build concavities. Enclosures are obtained as a particular case of concavities. Examples are shown in the context of suburban area and more particularly in house images. We also discuss, about the limits of this approach in terms of information provided by the edge masks and propose some improvements in order to extend our concavity definition.
- Bie-85.Biederman (I.), Human Image Understanding: Recent Research and a Theory, CVGIP, 32, 1985, 29–73.Google Scholar
- Dup-97.Duperthuy (C.), Jolion (J.M.), Toward a generalized primal sketch, 8th Int. Workshop on Theoretical Foundations of Computer Vision, Dagstuhl, Germany, 1996, Springer Verlag, Advances in Computing, 1997, 109–118.Google Scholar
- Min-88.Minsky (M.), Paperts (S.), Perceptrons, second edition, MIT Press, Cambridge, 1988.Google Scholar
- Mra-97.Mraghni (M.C.), Détection de chaînes de contours dans une image numérique par approche symbolique et par grammaire de formes, Ph.D. Thesis, Univ. of Tours, France, 1997.Google Scholar
- Net-87.Netanyahu (N.S.), Rosenfeld (A.), Mask matching for linear feature detection, Center for automation research technical report CS-TR-1759, 1987.Google Scholar
- Ros-82.Rosenfeld (A.), Kak (A.C.), Digital Picture Processing, second edition, Academic Press, 2(11), 1982.Google Scholar