Skip to Main content Skip to Navigation
Journal articles

Adaptive shape diagrams for multiscale morphometrical image analysis

Abstract : Shape diagrams are integral geometric representations in the Euclidean plane introduced to study 2D connected compact sets. Such a set is represented by a point within a shape diagram whose coordinates are morphometrical functionals defined as normalized ratios of geometrical functionals. In addition, the General Adaptive Neighborhoods (GANs) are spatial neighborhoods defined around each point of the spatial support of a gray-tone image, that fit with the image local structures. The aim of this paper is to introduce and study the GAN-based shape diagrams, which allow a gray-tone image morphometrical analysis to be realized in a local, adaptive and multiscale way. The GANbased shape diagrams will be illustrated on standard images and also applied in the biomedical and materials areas.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-01003567
Contributor : Andrée-Aimée Toucas Connect in order to contact the contributor
Submitted on : Tuesday, June 10, 2014 - 2:08:45 PM
Last modification on : Monday, October 18, 2021 - 4:22:02 PM

Identifiers

Citation

Séverine Rivollier, Johan Debayle, Jean-Charles Pinoli. Adaptive shape diagrams for multiscale morphometrical image analysis. Journal of Mathematical Imaging and Vision, Springer Verlag, 2014, 49 (1), pp.51-69. ⟨10.1007/s10851-013-0439-2⟩. ⟨hal-01003567⟩

Share

Metrics

Record views

384