Please use this identifier to cite or link to this item:
Type: Artigo
Title: An iterative spanning forest framework for superpixel segmentation
Author: Vargas-Muñoz, John E.
Chowdhury, Ananda S.
Alexandre, Eduardo B.
Galvão, Felipe L.
Miranda, Paulo A. Vechiatto
Falcão, Alexandre X.
Abstract: Superpixel segmentation has emerged as an important research problem in the areas of image processing and computer vision. In this paper, we propose a framework, namely Iterative Spanning Forest (ISF), in which improved sets of connected superpixels (supervoxels in 3D) can be generated by a sequence of image foresting transforms. In this framework, one can choose the most suitable combination of ISF components for a given application-i.e., 1) a seed sampling strategy; 2) a connectivity function; 3) an adjacency relation; and 4) a seed pixel recomputation procedure. The superpixels in ISF structurally correspond to spanning trees rooted at those seeds. We present five ISF-based methods to illustrate different choices for those components. These methods are compared with a number of state-of-the-art approaches with respect to effectiveness and efficiency. Experiments are carried out on several datasets containing 2D and 3D objects with distinct texture and shape properties, including a high-level application, named sky image segmentation. The theoretical properties of ISF are demonstrated in the supplementary material and the results show ISF-based methods rank consistently among the best for all datasets
Subject: Florestas
Country: Estados Unidos
Editor: IEEE Signal Processing Society
Rights: Fechado
Identifier DOI: 10.1109/TIP.2019.2897941
Date Issue: Jul-2019
Appears in Collections:IC - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
000469374100011.pdf2.61 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.