Unsupervised Morphological Multiscale Segmentation of Scanning Electron Microscopy Images

Gianni Franchi (1) , Jesus Angulo (1) , Maxime Moreaud (2)

1 CMM - Centre de Morphologie Mathématique
2 IFPEN - IFP Energies nouvelles

This paper deals with a problem of unsupervised multiscale segmentation in the domain of scanning electron microscopy, which is tackled by mathematical morphology techniques. The proposed approach includes various steps. First, the image is decomposed into various compact scales of representation, where objects at each scale are homogeneous in size. Multiscale decomposition is based on a morphological scale-space followed by scale merging using hierarchical clustering and earth mover distance. Then the compact scales are segmented independently using watershed transform. Finally the segmented scales are combined using a tree of objects in order to obtain a multiscale segmentation.

Mots clés: image processing; mathematical morphology; scanning electron microscopy

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Gianni Franchi, Jesus Angulo, Maxime Moreaud. Unsupervised Morphological Multiscale Segmentation of Scanning Electron Microscopy Images. 2014. ⟨hal-00939242⟩