Affiliations: [a] Instituto de Cibernática, Matemática y Física (ICIMAF), Grupo de Procesamiento Digital de Señales, Habana, Cuba
| [b] Instituto de Biotecnología, Universidad Nacional Autónoma de México (UNAM), Cuernavaca, Morelos, México | [c] Universidad Autónoma del Estado de Morelos (UAEM), Centro de Investigación en Ciencias, Instituto de Investigación en Ciencias Ba sicas y Aplicadas, México | [d] Instituto Polite cnico Nacional (IPN), Centro de Investigación en Computación (CIC), México | [e] Instituto Politécnico Nacional (IPN), Unidad Profesional Interdisciplinaria en Ingeniería y Tecnologías Avanzadas (UPIITA), México | [f] Tecnológico de Monterrey, Campus Guadalajara, Zapopan, Jalisco, México
Correspondence:
[*]
Corresponding author. Roberto Rodríguez, Instituto de Cibernética, Matemática
y Física (ICIMAF), Grupo de Procesamiento Digital de Señales, Habana, Cuba.
E-mail: rrm@icimaf.cu.
Abstract: Entropy has been used in many fields of computer vision, like image restoration, edge detection, pattern recognition, and as an evaluation method for image segmentation. The mean shift iterative algorithm (MSHi) was proposed in 2006, where the Shannon entropy was used as a stopping criterion. Later, it was introduced a theorem where this ensures, with a new stopping criterion, the convergence of the MSHi and determines what happens with the entropy at the limit of the segmentation process. The goal of this paper is carry out an analysis of the implications of this theorem and highlight the relation that were found from a physical point of view with image segmentation and the information theory. This last aspect being the novel part of this work.
