By normalizing the values of its pixels with respect to the lenght of the gray scale used, a monochromatic image is interpreted as a fuzzy relation R. We find the GEFS (resp. SEFS) of R, that is the greatest (resp. smallest) eigennfuzzy set with respect to the max-min (resp. min-max) composition. The reconstruction of R is achieved via a genetic algorithm whose initial population of chromosomes is formed by random gray images. The fitness function is based on the GEFS and SEFS of R and of each image-chromosome: the reconstructed imageis the image-chromosome with the highest fitness value. In our tests we haveused 350 images of sizes 256 × 256 extracted from the SIDBA image datasetconsisting of 10000 images (www.cs.cmu.edu/~cil/ vision.html).

Eigen fuzzy sets and a genetic algorithm for image information reconstruction / DI MARTINO, Ferdinando; Sessa, Salvatore. - In: JOURNAL OF UNCERTAIN SYSTEMS. - ISSN 1752-8909. - STAMPA. - 4:3(2010), pp. 171-180.

Eigen fuzzy sets and a genetic algorithm for image information reconstruction

Ferdinando Di Martino;SESSA, SALVATORE
2010

Abstract

By normalizing the values of its pixels with respect to the lenght of the gray scale used, a monochromatic image is interpreted as a fuzzy relation R. We find the GEFS (resp. SEFS) of R, that is the greatest (resp. smallest) eigennfuzzy set with respect to the max-min (resp. min-max) composition. The reconstruction of R is achieved via a genetic algorithm whose initial population of chromosomes is formed by random gray images. The fitness function is based on the GEFS and SEFS of R and of each image-chromosome: the reconstructed imageis the image-chromosome with the highest fitness value. In our tests we haveused 350 images of sizes 256 × 256 extracted from the SIDBA image datasetconsisting of 10000 images (www.cs.cmu.edu/~cil/ vision.html).
2010
Eigen fuzzy sets and a genetic algorithm for image information reconstruction / DI MARTINO, Ferdinando; Sessa, Salvatore. - In: JOURNAL OF UNCERTAIN SYSTEMS. - ISSN 1752-8909. - STAMPA. - 4:3(2010), pp. 171-180.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/368377
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact