Image segmentation using dense and sparse hierarchies of superpixels

Autor: Felipe Lemes Galvão, Alexandre X. Falcão, Silvio Jamil Ferzoli Guimarães
Přispěvatelé: Institute of Computing [Campinas] (UNICAMP), Universidade Estadual de Campinas (UNICAMP), Pontifical Catholic University of Minas Gerais [Belo Horizonte]
Rok vydání: 2020
Předmět:
Computer science
Boundary (topology)
02 engineering and technology
01 natural sciences
Image Foresting Transform
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]
Artificial Intelligence
0103 physical sciences
0202 electrical engineering
electronic engineering
information engineering
2010 MSC: 00-01
99-00
Segmentation
010306 general physics
Graph-based Image Segmentation
Iterative Spanning Forest
Hierarchy
Intersection (set theory)
business.industry
Hierarchical Image Segmentation
Pattern recognition
Irregular Image Pyramid
Image segmentation
Superpixel Segmentation
Object (computer science)
[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]
Computer Science::Computer Vision and Pattern Recognition
Signal Processing
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
business
Software
Zdroj: Pattern Recognition
Pattern Recognition, Elsevier, 2020, 108, pp.107532. ⟨10.1016/j.patcog.2020.107532⟩
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2020.107532
Popis: International audience; We investigate the intersection between hierarchical and superpixel image segmentation. Two strategies are considered: (i) the classical region merging, that creates a dense hierarchy with a higher number of levels, and (ii) the recursive execution of some superpixel algorithm, which generates a sparse hierarchy with fewer levels. We show that, while dense methods can capture more intermediate or higher-level object information, sparse methods are considerably faster and usually with higher boundary adherence at finer levels. We first formalize the two strategies and present a sparse method, which is faster than its superpixel algorithm and with similar boundary adherence. We then propose a new dense method to be used as post-processing from the intermediate level, as obtained by our sparse method, upwards. This combination results in a unique strategy and the most effective hierarchical segmentation method among the compared state-of-the-art approaches, with efficiency comparable to the fastest superpixel algorithms.
Databáze: OpenAIRE
Externí odkaz: