Skip to Main content Skip to Navigation
Journal articles

Hierarchical Segmentation Using Tree-Based Shape Spaces

Abstract : Current trends in image segmentation are to compute a hierarchy of image segmentations from fine to coarse. A classical approach to obtain a single meaningful image partition from a given hierarchy is to cut it in an optimal way, following the seminal approach of the scale-set theory. While interesting in many cases, the resulting segmentation, being a non-horizontal cut, is limited by the structure of the hierarchy. In this paper, we propose a novel approach that acts by transforming an input hierarchy into a new saliency map. It relies on the notion of shape space: a graph representation of a set of regions extracted from the image. Each region is characterized with an attribute describing it. We weigh the boundaries of a subset of meaningful regions (local minima) in the shape space by extinction values based on the attribute. This extinction-based saliency map represents a new hierarchy of segmentations highlighting regions having some specific characteristics. Each threshold of this map represents a segmentation which is generally different from any cut of the original hierarchy. This new approach thus enlarges the set of possible partition results that can be extracted from a given hierarchy. Qualitative and quantitative illustrations demonstrate the usefulness of the proposed method.
Complete list of metadata

Cited literature [54 references]  Display  Hide  Download
Contributor : Laurent Najman <>
Submitted on : Wednesday, April 13, 2016 - 1:21:07 PM
Last modification on : Wednesday, June 9, 2021 - 5:28:03 PM
Long-term archiving on: : Thursday, July 14, 2016 - 5:35:44 PM

Files produced by the author(s)



Yongchao Xu, Edwin Carlinet, Thierry Géraud, Laurent Najman. Hierarchical Segmentation Using Tree-Based Shape Spaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2017, 39 (3), pp.457-469. ⟨10.1109/TPAMI.2016.2554550⟩. ⟨hal-01301966⟩



Record views


Files downloads