Skip to Content

Generating segmented meshes from textured color images


This paper presents a new framework for generating triangular meshes from textured color images. The proposed framework combines a texture classification technique, called W-operator, with Imesh, a method originally conceived to generate simplicial meshes from gray scale images. An extension of Woperators to handle textured color images is proposed, which employs a combination of RGB and HSV channels and Sequential Floating Forward Search guided by mean conditional entropy criterion to extract features from the training data. The W-operator is built into the local error estimation used by Imesh to choose the mesh vertices. Furthermore, the W-operator also enables to assign a label to the triangles during the mesh construction, thus allowing to obtain a segmented mesh at the end of the process. The presented results show that the combination of W-operators with Imesh gives rise to a texture classification based triangle mesh generation framework that outperforms pixel based methods. 

Mario A.S. Lizier
David C. Martins Jr
Alex J. Cuadros-Vargas
Roberto M. Cesar Jr.
Luis G. Nonato
Informações Relevantes
Ano de Publicação: 
Download da Publicação: 
Informações do Laboratório
Linhas de Pesquisa: