Centre de documentation
scientifique

Hybrid image noise reduction algorithm based on genetic ant colony and PCNN / Chong Shen in The Visual Computer, vol 33 n° 11 (November 2017)  

Public [article]  inThe Visual Computer > vol 33 n° 11 (November 2017) . - pp 1373 - 1384 Titre : Hybrid image noise reduction algorithm based on genetic ant colony and PCNN Type de document : Article/Communication Auteurs : Chong Shen, Auteur ; Ding Wang, Auteur ; Shuming Tang, Auteur ; Huiliang Cao, Auteur ; Jun Liu, Auteur Année de publication : 2017 Article en page(s) : pp 1373 - 1384 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] algorithme génétique [Termes IGN] filtrage du bruit [Termes IGN] optimisation par colonie de fourmis [Termes IGN] réseau neuronal artificiel Résumé : (Auteur) Pulse Coupled Neural Network (PCNN) has gained widespread attention as a nonlinear filtering technology in reducing the noise while keeping the details of images well, but how to determine the proper parameters for PCNN is a big challenge. In this paper, a method that can optimize the parameters of PCNN by combining the genetic algorithm (GA) and ant colony algorithm is proposed, which named as GACA, and the optimized procedure is named as GACA-PCNN. Firstly, the noisy image is filtered by median filter in the proposed GACA-PCNN method; then, the noisy image is filtered by GACA-PCNN constantly and the median filtering image is used as a reference image; finally, a set of parameters of PCNN can be automatically estimated by GACA, and the pretty effective denoising image will be obtained. Experimental results indicate that GACA-PCNN has a better performance on PSNR (peak signal noise rate) and a stronger capacity of preserving the details than previous denoising techniques. Numéro de notice : A2017-712 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1007/s00371-016-1325-x En ligne : https://doi.org/10.1007/s00371-016-1325-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88093 [article]