On the Role of Contrast and Regularity in Perceptual Boundary Saliency - Archive ouverte HAL Access content directly
Journal Articles Journal of Mathematical Imaging and Vision Year : 2013

On the Role of Contrast and Regularity in Perceptual Boundary Saliency

(1) , (2) , (3, 4)
1
2
3
4

Abstract

Mathematical Morphology proposes to extract shapes from images as connected components of level sets. These methods prove very suitable for shape recognition and analysis. We present a method to select the perceptually significant (i.e., contrasted) level lines (boundaries of level sets), using the Helmholtz principle as first proposed by Desolneux et al. Contrarily to the classical formulation by Desolneux et al. where level lines must be entirely salient, the proposed method allows to detect partially salient level lines, thus resulting in more robust and more stable detections. We then tackle the problem of combining two gestalts as a measure of saliency and propose a method that reinforces detections. Results in natural images show the good performance of the proposed methods.
Fichier principal
Vignette du fichier
meaningfulBoundaries-release4-hal.pdf (6.31 Mo) Télécharger le fichier
Vignette du fichier
boat (1).png (196.65 Ko) Télécharger le fichier
Vignette du fichier
boat - MCRB.pdf (819.16 Ko) Télécharger le fichier
Vignette du fichier
boat - MCRB.png (68.83 Ko) Télécharger le fichier
Vignette du fichier
boat.pdf (819.16 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Comment : vignette 1
Format : Figure, Image
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Comment : vignette 2
Loading...

Dates and versions

hal-00803806 , version 1 (26-03-2015)

Identifiers

Cite

Mariano Tepper, Pablo Musé, Andrés Almansa. On the Role of Contrast and Regularity in Perceptual Boundary Saliency. Journal of Mathematical Imaging and Vision, 2013, 48 (3), pp.396-412. ⟨10.1007/s10851-012-0411-6⟩. ⟨hal-00803806⟩
401 View
152 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More