| Full text | |
| Author(s): |
Casanova, D.
;
Florindo, J. B.
;
Falvo, M.
;
Bruno, O. M.
Total Authors: 4
|
| Document type: | Journal article |
| Source: | INFORMATION SCIENCES; v. 346, p. 58-72, JUN 10 2016. |
| Web of Science Citations: | 13 |
| Abstract | |
This work presents a method for color texture analysis based on fractal geometry. The method is based on its predecessor {[}4] and consists of mapping each color channel onto a surface and dilating such surface by spheres with a variable radius. The descriptors are obtained from the relation between the volumes of the dilated surfaces and the dilation radii. The dilation process creates a mutual interference among the color channels. The proposed descriptors measure the degree of such interference as well as the complexity of pixel intensity arrangements. This combination provides a robust and precise texture description. The efficiency of the method is assessed in a classification task of well-known texture data sets and the results demonstrate that it outperforms the best approaches described in the literature. (C) 2016 Published by Elsevier Inc. (AU) | |
| FAPESP's process: | 11/01523-1 - Computer vision methods applied to the identification and analysis of plants |
| Grantee: | Odemir Martinez Bruno |
| Support Opportunities: | Regular Research Grants |
| FAPESP's process: | 12/19143-3 - Fractal Geometry and Image Analysis Applied to Vegetal Biology |
| Grantee: | Joao Batista Florindo |
| Support Opportunities: | Scholarships in Brazil - Post-Doctoral |
| FAPESP's process: | 13/22205-3 - Tissue spatial organization and fractal analyses for automated plant taxonomy |
| Grantee: | Joao Batista Florindo |
| Support Opportunities: | Scholarships abroad - Research Internship - Post-doctor |