Please use this identifier to cite or link to this item:
Title: An attribute-based image segmentation method
Title of periodic: Materials Research São Carlos
Authors: Andrade, Marcos Carneiro de
Bertrand, G.
Araújo, A.A. de
Affiliation: Centro de Desenvolvimento da Tecnologia Nuclear/CDTN, Belo Horizonte, MG, Brasil
École Supérieure d'Ingénieurs en Electrotechnique et Electronique/ESIEE, Noisy-le-Grand, France
Universidade Federal de Minas Gerais/UFMG, Belo Horizonte, MG, Brasil
Issue Date: 1999
Keywords: Image;grain size;ceramics;uranium oxides
Abstract: This work addresses a new image segmentation method founded on Digital Topology and Mathematical Morphology grounds. The ABA (attribute based absorptions) transform can be viewed as a region-growing method by flooding simulation working at the scale of the main structures of the image. In this method, the gray level image is treated as a relief flooded from all its local minima, which are progressively detected and merged as the flooding takes place. Each local minimum is exclusively associated to one catchment basin (CB). The CBs merging process is guided by their geometric parameters as depth, area and/or volume. This solution enables the direct segmentation of the original image without the need of a preprocessing step or the explicit marker extraction step, often required by other flooding simulation methods. Some examples of image segmentation, employing the ABA transform, are illustrated for uranium oxide samples. It is shown that the ABA transform presents very good segmentation results even in presence of noisy images. Moreover, it's use is often easier and faster when compared to similar image segmentation methods.
Access: L
Appears in Collections:Artigo de periódico

Files in This Item:
File Description SizeFormat 
Art-01_MarcosCarneiro_Andrade.pdf628.85 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.