Supervised and unsupervised segmentation of textured images by efficient multi-level pattern classification

This thesis proposes new, efficient methodologies for supervised and unsupervised image segmentation based on texture information. For the supervised case, a technique for pixel classification based on a multi-level strategy that iteratively refines the resulting segmentation is proposed. This strat...

Descripción completa

Detalles Bibliográficos
Autor: Meléndez Rodríguez, Jaime Christian
Tipo de recurso: tesis doctoral
Estado:Versión publicada
Fecha de publicación:2010
País:España
Institución:CBUC, CESCA
Repositorio:TDR. Tesis Doctorales en Red
OAI Identifier:oai:www.tdx.cat:10803/8487
Acceso en línea:http://www.tdx.cat/TDX-1108110-100919
http://hdl.handle.net/10803/8487
Access Level:acceso abierto
Palabra clave:support vector machines
prototype-based classification
multi-level classification
multi-sized evaluation windonws
supervised pixel-based classification
unsupervised texture segmentation
supervised texture segmentation
004
Descripción
Sumario:This thesis proposes new, efficient methodologies for supervised and unsupervised image segmentation based on texture information. For the supervised case, a technique for pixel classification based on a multi-level strategy that iteratively refines the resulting segmentation is proposed. This strategy utilizes pattern recognition methods based on prototypes (determined by clustering algorithms) and support vector machines. In order to obtain the best performance, an algorithm for automatic parameter selection and methods to reduce the computational cost associated with the segmentation process are also included. For the unsupervised case, the previous methodology is adapted by means of an initial pattern discovery stage, which allows transforming the original unsupervised problem into a supervised one. Several sets of experiments considering a wide variety of images are carried out in order to validate the developed techniques.