Waterpixels and their Application to Image Segmentation Learning
PhD Project, under the direction of Etienne Decencière and Thomas Walter
Waterpixels: Superpixels Based on the Watershed Transformation
Oct. 2013 - Jan. 2015
We focus on the partition of the image into small regular homogeneous regions called superpixels. The latter are very useful as they typically serve as primitives for further analysis of the image such as detection, segmentation and classification of objects.
We propose a new method based on the watershed transformation to generate superpixels, called waterpixels.
Learning Image Segmentation with Waterpixels
Feb. 2015 - Dec. 2016
Waterpixels can be a pertinent tool for image segmentation learning, e.g. when the latter is seen as a classification task. Whereas superpixels are often used in the literature as primitives in such pipeline, we propose in this work to use them as support to compute new features for pixel classification. We call such features "SAF" (Superpixel-Adaptive Features).
