Adaptive texture image segmentation using local-base pyramids
Hubert Konik,
Laboratoire Traitement du Signal et Instrumentation, 23, rue du Dr P. Michelon, 42023 Saint-Etienne Cedex 2, France
Maurice Calonnier,
Institut Textile de France, Av. Guy de Collongue B.P. 60, 69132 Ecully Cedex, France
Bernard Laget,
Laboratoire Traitement du Signal et Instrumentation, 23, rue du Dr P. Michelon, 42023 Saint-Etienne Cedex 2, France
Abstract
This paper presents an approach to textured image segmentation. It is more exactly intended for detecting and extracting compact objects from an image. Because multiresolution or pyramidal techniques set problems, local-base pyramids are introduced. They are called "local pyramids" and simulate the human vision in its attention focusing process. Moreover, our method has the advantage to be adaptive with respect to the image texture.
Keywords : image segmentation, local methods, pyramid, texture
Pour citer cet article
Hubert Konik, Maurice Calonnier & Bernard Laget, «Adaptive texture image segmentation using local-base pyramids», Acta Stereologica [En ligne], Volume 13 (1994), Number 2 - Proceedings of the sixth European congress for stereology - Part three - June 1994, 499-504 URL : https://popups.uliege.be/0351-580x/index.php?id=4383.