Image Threshold Using A-IFSs Based on Bounded Histograms

  • Authors:

  • Pedro Couto;Humberto Bustince;Vitor Filipe;Edurne Barrenechea;Miguel Pagola;Pedro Melo-Pinto

  • Affiliations:

  • CETAV --- University of Trás-os-Montes e Alto Douro, Ap. 1014, 5001-911 Vila Real, Portugal;Departamento de Automática y Computación - Universidad Pública de Navarra, Campus de Arrosadía, s/n, 31006 Pamplona, Spain;CETAV --- University of Trás-os-Montes e Alto Douro, Ap. 1014, 5001-911 Vila Real, Portugal;Departamento de Automática y Computación - Universidad Pública de Navarra, Campus de Arrosadía, s/n, 31006 Pamplona, Spain;Departamento de Automática y Computación - Universidad Pública de Navarra, Campus de Arrosadía, s/n, 31006 Pamplona, Spain;CETAV --- University of Trás-os-Montes e Alto Douro, Ap. 1014, 5001-911 Vila Real, Portugal

  • Venue:
  • IFSA '07 Proceedings of the 12th international Fuzzy Systems Association world congress on Foundations of Fuzzy Logic and Soft Computing
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Atanassov's intuitionistic fuzzy sets (A-IFSs) have been used recently to determine the optimal threshold value for gray-level image segmentation [1]. Atanassov's intuitionistic fuzzy index values are used for representing the unknowledge/ignorance of an expert on determining whether a pixel of the image belongs to the background or the object of the image. This optimal global threshold of the image is computed automatically, regardless of the actual image analysis process.Although global optimal thresholding techniques give good results under experimental conditions, when dealing with real images having several objects and the segmentation purpose is to point out some application-specific information, one should use heuristic techniques in order to obtain better thresholding results.This paper introduces an evolution of the above mentioned technique intended for use with such images. The proposed approach takes into account the image and segmentation specificities by using a two-step procedure, with a restricted set of the image gray-levels.Preliminary experimental results and comparison with other methods are presented.