On the Role of Contrast and Regularity in Perceptual Boundary Saliency

Mariano Tepper (1) , Pablo Musé (2) , Andrés Almansa (3, 4)

1 Departamento de Computación [Buenos Aires]
2 IIE - Instituto de Ingeniería Eléctrica
3 INCO - Instituto de Computacion [Montevideo]
4 LTCI - Laboratoire Traitement et Communication de l'Information

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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]; Traitement du signal et de l'image [eess.SP]; Analyse numérique [math.NA]

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⟩