Image segmentation based on ultimate levelings: From attribute filters to machine learning strategies

Autor(es)

Alves, Wonder A. L. ^[1] ; Gobber, Charles F. ^[1] ; Silva, Dennis J. ^[2] ; Morimitsu, Alexandre ^[2] ; Hashimoto, Ronaldo F. ^[2] ; Marcotegui, Beatriz ^[3]

Afiliação do(s) autor(es)

^[1] Univ Nave Julho, Informat & Knowledge Management Grad Program, Sao Paulo - Brazil

^[2] Univ Sao Paulo, Inst Math & Stat, Dept Comp Sci, Sao Paulo - Brazil

^[3] Mines ParisTech, Ctr Math Morphol, Fontainebleau - France

• Tipo de documento: Artigo Científico
• Fonte: PATTERN RECOGNITION LETTERS; v. 133, p. 264-271, MAY 2020.
• Citações Web of Science: 0

Resumo

Ultimate levelings are operators that extract important image contrast information from a scale-space based on levelings. Along with the residual extraction process, some residues usually come from undesirable regions, and they should be filtered out. For this, some strategies can be applied to filter these undesirable residues. In this paper, we introduce a new approach to detect desirable regions from ultimate levelings through a new hierarchical structure called residual tree. From this structure, we extract attribute vectors to build a machine learning model which gives a matching value between ground truth regions and residual tree nodes. Thus, from the selected residual tree nodes, we present a new approach to choose the best disjoint residual nodes which gives the regions of the ultimate levelings. Finally, from the ultimate levelings, we use its partition associated function to solve the segmentation problem. In order to evaluate our new approach, some experiments were carried out with a plant dataset and results report the state-of-the-art performance in plant segmentation. (C) 2020 Elsevier B.V. All rights reserved. (AU)

• Processo FAPESP: 18/15652-7 - Segmentação de imagens baseada em restrições de formas por meio dos últimos levelings
• Beneficiário: Wonder Alexandre Luz Alves
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 15/01587-0 - Armazenagem, modelagem e análise de sistemas dinâmicos para aplicações em e-Science
• Beneficiário: João Eduardo Ferreira
• Modalidade de apoio: Auxílio à Pesquisa - Programa eScience e Data Science - Temático