Unsupervised Image Segmentation Based on Local pixel Clustering and Low-Level Region Merging - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Unsupervised Image Segmentation Based on Local pixel Clustering and Low-Level Region Merging

Résumé

Heterogeneous image segmentation is one of the most important tasks in image processing. It consists in partitioning the image into a set of disjoint regions. In this paper, we propose a new unsupervised image segmentation method that we call Unsupervised Image Segmentation (UIS). Our proposal performs an efficient image partition efficiently into primitive regions. This process is ensured by a local adaptive Kmeans and a novel centroids initialization. Then, similar sets are agglomerated to form homogeneous regions. For that, a low-level feature merging is employed according to a hierarchical linkage approach. Finally, in case of over-segmentation, appearing outlier regions are removed using a post process stage. Therefore, the UIS method allows to determine automatically the image region number. Indeed, it extends the Kmeans clustering to obtain meaningful regions. Several experiments were conducted using two heterogeneous image datasets. A comparison with well-known segmentation methods was also performed using the Liu's factor measure.
Fichier principal
Vignette du fichier
ATSIP_2016.pdf (1.53 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01309999 , version 1 (01-05-2016)

Identifiants

  • HAL Id : hal-01309999 , version 1

Citer

Rostom Kachouri, Mahmoud Soua, Mohamed Akil. Unsupervised Image Segmentation Based on Local pixel Clustering and Low-Level Region Merging. 2nd IEEE International Conference on Advanced Technologies for Signal and Image Processing ATSIP'16, Mar 2016, Monastir, Tunisia. ⟨hal-01309999⟩
180 Consultations
1853 Téléchargements

Partager

Gmail Facebook X LinkedIn More