Diferencia entre revisiones de «Hybrid Image Segmentation»

De Grupo de Inteligencia Computacional (GIC)
Sin resumen de edición
Sin resumen de edición
 
(No se muestran 10 ediciones intermedias de 2 usuarios)
Línea 1: Línea 1:
: In this page we make publicly available a demonstration of  a hybrid image segmentation method based on a hybrid distance which is inspired in the selective behavior of the human vision system.  
: In this page we make publicly available a demonstration of  a [[media:HIS.zip| Hybrid Image Segmentation]] method based on a hybrid distance which is inspired in the selective behavior of the human vision system.  
: The method has 3 parameters (a,b,c) to control the hybridation of activation energies, and by other hand a threshol. The threshold model the amount of regions.
 
: As we explain in our works, image segmentation is a human hability, therefore it's dificult to compute it. In different occasion we will wish diferent segmentation. Helping to his goal, we share this sofware [[media:HIS.zip|HIS]]. Using it, we can know the parameters (a,b,c) and the threshold.
: The method has 3 parameters (a,b,c) that specify the mixture model controlling the of activation of each component of the hybrid distance. Besides, the method allows the specification of a decision threshold controlling the sensitivity of the method and the resulting amount of image segmentation regions.
: This sofware is for .Net platform.
: The details of the method are given in the paper
    ''Image Segmentation on the Spherical Coordinate Representation of the RGB Color Space''
    R. Moreno, D. M. Ramik, M. Graña, and K. Madani, IET Image processing (2013), 6(9):1275 - 1283
 
: The [[media:SphericClass.zip| Sources]]. This class in C# and contains a lot of methods for image segmentation based on the spheric approach.
: For any question, fell free to ask [http://www.ehu.es/ccwintco/index.php/Usuario:Natafresa me].
: Platform support: This software has been developed in the .Net platform.

Revisión actual - 00:41 20 mar 2014

In this page we make publicly available a demonstration of a Hybrid Image Segmentation method based on a hybrid distance which is inspired in the selective behavior of the human vision system.
The method has 3 parameters (a,b,c) that specify the mixture model controlling the of activation of each component of the hybrid distance. Besides, the method allows the specification of a decision threshold controlling the sensitivity of the method and the resulting amount of image segmentation regions.
The details of the method are given in the paper
   Image Segmentation on the Spherical Coordinate Representation of the RGB Color Space
   R. Moreno, D. M. Ramik, M. Graña, and K. Madani, IET Image processing (2013), 6(9):1275 - 1283
The Sources. This class in C# and contains a lot of methods for image segmentation based on the spheric approach.
For any question, fell free to ask me.
Platform support: This software has been developed in the .Net platform.