Evaluation of hierarchical watersheds - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Image Processing Year : 2018

Evaluation of hierarchical watersheds

Abstract

This article aims to understand the practical features of hierarchies of morphological segmentations, namely the quasi-flat zones hierarchy and watershed hierarchies, and to evaluate their potential in the context of natural image analysis. We propose a novel evaluation framework for hierarchies of partitions designed to capture various aspects of those representations: precision of their regions and contours, possibility to extract high quality horizontal cuts and optimal non-horizontal cuts for image segmentation, and ease of finding a set of regions representing a semantic object. This framework is used to assess and to optimize hierarchies with respect to the possible pre-and post-processing steps. We show that, used in conjunction with a state-of-the art contour detector, watershed hierarchies are competitive with complex state of the art methods for hierarchy construction. In particular, the proposed framework allows us to identify a watershed hierarchy based on a novel extinction value, the number of parent nodes, that outperforms the other hierarchies of morphological segmentations. This coupled with the fact that watershed hierarchies satisfy clear global optimality properties and can be computed efficiently on large data, make them valuable candidates for various computer vision tasks.
Fichier principal
Vignette du fichier
PCGM - TIP 2018 - Evaluation of hierarchical watersheds.pdf (2.41 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01430865 , version 1 (10-01-2017)
hal-01430865 , version 2 (16-01-2017)
hal-01430865 , version 3 (19-10-2017)
hal-01430865 , version 4 (09-01-2018)

Identifiers

Cite

Benjamin Perret, Jean Cousty, Silvio J.F. Guimarães, Deise S Maia. Evaluation of hierarchical watersheds. IEEE Transactions on Image Processing, 2018, 27 (4), pp.1676-1688. ⟨10.1109/TIP.2017.2779604⟩. ⟨hal-01430865v4⟩
516 View
860 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More