An efficient combination of texture and color information for watershed segmentation
Résumé
A new segmentation technique based on a color watershed using an adaptive combination of color and texture information is pro- posed on this paper. This information is represented by two morpholog- ical gradients, a classical color gradient and a texture gradient based on co-occurrence matrices texture features. The two morphological gradi- ents are then mixed using a gradient component fusion strategy and an adaptive technique to choose the weighting coefficients. The segmenta- tion process is finally performed by applying the watershed algorithm. The obtained results are then evaluated with the MSE for several sets of parameters and color spaces.
Origine | Fichiers produits par l'(les) auteur(s) |
---|