Busca avançada
Ano de início
Entree


Novel Arc-Cost Functions and Seed Relevance Estimations for Compact and Accurate Superpixels

Texto completo
Autor(es):
Belem, Felipe C. C. ; Barcelos, Isabela B. B. ; Joao, Leonardo M. M. ; Perret, Benjamin ; Cousty, Jean ; Guimaraes, Silvio J. F. ; Falcao, Alexandre X. X.
Número total de Autores: 7
Tipo de documento: Artigo Científico
Fonte: Journal of Mathematical Imaging and Vision; v. 65, n. 5, p. 17-pg., 2023-08-16.
Resumo

On the verge of superpixel methods exploiting saliency information, the Superpixels through Iterative CLEarcutting (SICLE) framework has reported fast and accurate superpixel delineation. It is composed of three steps: (i) seed oversampling; (ii) superpixel generation; and (iii) seed removal. It starts from (i) and applies several iterations of (ii) and (iii) until reaching the desired superpixel quantity. In this work, we improve SICLE such that it can now generate compact superpixels with accurate delineation. We exploit differential computation and propose several novel functions for steps (ii) and (iii) for proper saliency incorporation, compact superpixel generation, and improvement in speed and delineation. Results show that, with our proposals, SICLE achieves state-of-the-art performance in delineation and speed whenever saliency is absent with on-par compacity. When an accurate saliency map is provided, its performance improves significantly and requires only two iterations for segmentation. (AU)

Processo FAPESP: 14/12236-1 - AnImaLS: Anotação de Imagem em Larga Escala: o que máquinas e especialistas podem aprender interagindo?
Beneficiário:Alexandre Xavier Falcão
Modalidade de apoio: Auxílio à Pesquisa - Temático