%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi@80/2006/08.24.16.48
%2 sid.inpe.br/sibgrapi@80/2006/08.24.16.48.49
%@doi 10.1109/SIBGRAPI.2006.26
%T Improving 2D mesh image segmentation with Markovian Random Fields
%D 2006
%A Cuadros-Vargas, Alex J.,
%A Gerhardinger, Leandro C.,
%A Castro, Mário,
%A Batista Neto, João,
%A Nonato, Luis G.,
%@affiliation ICMC - Instituto de Ciências Matemáticas e de Computação - USP
%@affiliation ICMC - Instituto de Ciências Matemáticas e de Computação - USP
%@affiliation ICMC - Instituto de Ciências Matemáticas e de Computaão - USP
%@affiliation ICMC - Instituto de Ciências Matemáticas e de Computaão - USP
%@affiliation ICMC - Instituto de Ciências Matemáticas e de Computaão - USP
%E Oliveira Neto, Manuel Menezes de,
%E Carceroni, Rodrigo Lima,
%B Brazilian Symposium on Computer Graphics and Image Processing, 19 (SIBGRAPI)
%C Manaus, AM, Brazil
%8 8-11 Oct. 2006
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%K Polygonal Meshes, Texture Analysis, Segmentation.
%X Traditional mesh segmentation methods normally operate on geometrical models with no image information. On the other hand, 2D image-based mesh generation and segmentation counterparts, such as Imesh \cite{Vargas:05} perform the task by following a set of well defined rules derived from the geometry of the triangles, but with no statistical information of the mesh elements. This paper presents a novel segmentation method that combines the original Imesh image-based segmentation approach with Markovian Random Field (MRF) models. It takes an image as input, generate a mesh of triangles and, by treating the mesh as a Markovian field, produces quality unsupervised segmentation. The results have demonstrated that the method not only provides better segmentation than that of original Imesh, but is also capable of producing MRF-like segmentation output for certain types of images, with considerable cut in processing times.
%@language en
%3 Vargas-MRF_Mesh.pdf