ISSN:
1573-7470
Quelle:
Springer Online Journal Archives 1860-2000
Thema:
Informatik
,
Mathematik
Notizen:
Abstract A model-based vision system attempts to find correspondences between features of an object model and features detected in an image for purposes of recognition, localization, or inspection. In this paper we pose the relational matching problem as a special case of the pattern complex recognition problem and propose a probabilistic model to describe the images of an object. This Bayesian approach allows us to make explicit statements of how an image is formed from a model, and hence define a natural matching cost that can be used to guide a heuristic search in finding the best observation mapping. Furthermore, we show that even though the nature of the feature matching problem is exponential, the use of the proposed algorithm keeps the size of the problem under control, by efficiently reducing the search space.
Materialart:
Digitale Medien
URL:
http://dx.doi.org/10.1007/BF01530945
Permalink