Segmentation hiérarchique faiblement supervisée
This work addresses image segmentation for computer vision applications, but appears incremental as it builds on existing hierarchical methods with added prior information.
The paper tackles the problem of hierarchical image segmentation by incorporating prior spatial information to emphasize contours or regions of interest while preserving important structures, and demonstrates its application to weakly-supervised segmentation.
Image segmentation is the process of partitioning an image into a set of meaningful regions according to some criteria. Hierarchical segmentation has emerged as a major trend in this regard as it favors the emergence of important regions at different scales. On the other hand, many methods allow us to have prior information on the position of structures of interest in the images. In this paper, we present a versatile hierarchical segmentation method that takes into account any prior spatial information and outputs a hierarchical segmentation that emphasizes the contours or regions of interest while preserving the important structures in the image. An application of this method to the weakly-supervised segmentation problem is presented.