An Iterative Spanning Forest Framework for Superpixel Segmentation

DOI10.1109/TIP.2019.2897941MaRDI QIDQ5238363zbMATH OpenOpenAlexWikidataFDO

Authors John E. Vargas-Muñoz, Ananda S. Chowdhury, Eduardo B. Alexandre, Felipe L. Galvão, Paulo A. Vechiatto Miranda, Alexandre Falcao

Publication date 28 October 2019

Published in IEEE Transactions on Image Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1801.10041

Mathematics Subject Classification ID

Graph theory (including graph drawing) in computer science (68R10) Computing methodologies for image processing (68U10)

Abstract: Superpixel segmentation has become an important research problem in image processing. In this paper, we propose an Iterative Spanning Forest (ISF) framework, based on sequences of Image Foresting Transforms, where one can choose i) a seed sampling strategy, ii) a connectivity function, iii) an adjacency relation, and iv) a seed pixel recomputation procedure to generate improved sets of connected superpixels (supervoxels in 3D) per iteration. The superpixels in ISF structurally correspond to spanning trees rooted at those seeds. We present five ISF methods to illustrate different choices of its components. These methods are compared with approaches from the state-of-the-art in effectiveness and efficiency. The experiments involve 2D and 3D datasets with distinct characteristics, and a high level application, named sky image segmentation. The theoretical properties of ISF are demonstrated in the supplementary material and the results show that some of its methods are competitive with or superior to the best baselines in effectiveness and efficiency.

Cited in

(10)

• Prior-based hierarchical segmentation highlighting structures of interest
• Fast marching based superpixels
• Correction to: ``Rooted spanning superpixels
• Towards interactive image segmentation by dynamic and iterative spanning forest
• Graph-based supervoxel computation from iterative spanning forest
• The role of optimum connectivity in image segmentation: can the algorithm learn object information during the process?
• A Supervoxel-Based Solution to Resume Segmentation for Interactive Correction by Differential Image-Foresting Transforms
• Novel arc-cost functions and seed relevance estimations for compact and accurate superpixels
• Differential oriented image foresting transform and its applications to support high-level priors for object segmentation
• Differential oriented image foresting transform segmentation by seed competition

This page was built for publication: An Iterative Spanning Forest Framework for Superpixel Segmentation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5238363)