Automatic Object Modelization in Computer Vision

Patrick Gros (1, 2) , Roger Mohr (1, 2)

1 MOVI - Modeling, localization, recognition and interpretation in computer vision
2 LIFIA - Laboratoire d'Informatique Fondamentale et d'Intelligence Artificielle

In this paper, we present a general frame for an algorithm of automatic modelization. Built models are learned from examples; they consist mainly in contour feature structure with geometrical descriptors and reliability information. The two first stages of this algorithm are especially studied and experimental results are shown. These stages are the matching of two input images and the clustering of a set of images into a model group.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Patrick Gros, Roger Mohr. Automatic Object Modelization in Computer Vision. the International Workshop on Structural and Syntactic Pattern Recognition, Aug 1992, Bern, Switzerland. pp.385--400, ⟨10.1142/9789812797919_0032⟩. ⟨inria-00548440⟩