CIFASIS   20631
CENTRO INTERNACIONAL FRANCO ARGENTINO DE CIENCIAS DE LA INFORMACION Y DE SISTEMAS
Unidad Ejecutora - UE
artículos
Título:
Multifractal characterization and classi cation of bread crumb digital images
Autor/es:
BARAVALLE, RODRIGO; DELRIEUX, CLAUDIO; GOMEZ, JUAN CARLOS
Revista:
Signal, Image and Video Processing
Editorial:
Springer
Referencias:
Lugar: Berlin; Año: 2015 vol. 2015 p. 1 - 12
ISSN:
1863-1711
Resumen:
Adequate models of the bread crumb structure can be critical for understanding how and transport processes in bread, creating synthetic bread crumb images for photo-realistic rendering, evaluating similarities, and establishing quality features of di erent breadcrumb types. In this article multifractal analysis, employing the multifractal spectrum (MFS), has been applied to study the structure of the bread crumb in four varieties ofbread (baguette, sliced, bran, and sandwich). The extracted dimensions can be used to discriminate among bread crumbs from di erent types. Also, high correlations were found between some of these parameters and the porosity, coarseness, and heterogeneity of thesamples. These results demonstrate that the MFS is an appropriate tool for characterizing the internal structure of the bread crumb and thus it may be used to establish important quality properties it should have. The MFS has shown to provide local and global imagefeatures that are both robust and low-dimensional, leading to feature vectors that capture essential information for classication tasks. Based on this, in this work we also apply the MFS for bread crumb classification of slices of di erent bread types. Results show that the MFS based classication is able to distinguish diff erent bread crumbs with very high accuracy. Multifractal modeling of the bread crumb structure can be an appropriate method for parameterizing and simulating the appearance of di erent bread crumbs.