Automatic choice of the threshold of a grain filter via Galton-Watson trees. Application to granite cracks detection

Romain Abraham (1) , Maïtine Bergounioux (1) , Pierre Debs (1)

1 MAPMO - Mathématiques - Analyse, Probabilités, Modélisation - Orléans

The goal of this paper is the presentation of post-processing method allowing to remove impulse noise in binary images, while preserving thin structures. We use a grain filter as in [5]. We propose a method to automatically determine the required threshold using Galton-Watson processes. We present numerical results using X-tomography images of a granite block (2D and 3D) to illustrate how we get rid of the noise while cracks are kept.

Mots clés: Image processing; Galton-Watson; grain filter; cracks

Domaines: Probabilités [math.PR]; Traitement des images [eess.IV]

Romain Abraham, Maïtine Bergounioux, Pierre Debs. Automatic choice of the threshold of a grain filter via Galton-Watson trees. Application to granite cracks detection. 2016. ⟨hal-01337551v1⟩