General adaptive neighborhood viscous mathematical morphology

  • Authors:
  • Johan Debayle;Jean-Charles Pinoli

  • Affiliations:
  • Ecole Nationale Supérieure des Mines de Saint-Etienne, CIS-LPMG, UMR CNRS 5148, Saint-Etienne Cedex, France;Ecole Nationale Supérieure des Mines de Saint-Etienne, CIS-LPMG, UMR CNRS 5148, Saint-Etienne Cedex, France

  • Venue:
  • ISMM'11 Proceedings of the 10th international conference on Mathematical morphology and its applications to image and signal processing
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper is focused on adaptive viscous morphology in the context of the General Adaptive Neighborhood Image Processing (GANIP) approach [1,2]. A local adaptive neighborhood is defined for each image point, depending on the intensity function of the image. These so-called General Adaptive Neighborhoods (GANs) are used as adaptive structuring elements for Mathematical Morphology (MM) [1,3]. In this paper, GAN-based viscous MM is introduced to adjust the filtering activity to the image gray levels. The proposed GAN viscous morphological filters are successfully applied on real application examples in image restoration and enhancement.