Bagging Stochastic Watershed on Natural Color Image Segmentation
Abstract
The stochastic watershed is a probabilistic segmentation ap-proach which estimates the probability density of contours of the image from a given gradient. In complex images, the stochastic watershed can enhance insignificant contours. To partially address this drawback, we introduce here a fully unsupervised multi-scale approach including bag-ging. Re-sampling and bagging is a classical stochastic approach to im-prove the estimation. We have assessed the performance, and compared to other version of stochastic watershed, using the Berkeley segmentation database.
Fichier principal
Bagging_Stochastic_Watershed_FRANCHI_ANGULO_V2.pdf (592.64 Ko)
Télécharger le fichier
Origin : Files produced by the author(s)
Loading...