{"title":"An Improved Progressive Switching Median Filter","authors":"Soon Ting Boo, H. Ibrahim, K. Toh","doi":"10.1109/ICFCC.2009.87","DOIUrl":null,"url":null,"abstract":"The progressive switching median (PSM) filter implements a noise detection algorithm before filtering. Both noise detection and filtering procedures are progressively repeated for a number of iterations. As an attempt to improve the PSM filter, an improved progressive switching median filter (IPSM) is proposed to enhance progressive median filter in term of its noise filtering ability. The proposed algorithm sets a limit on the number of good pixels used in determine median and mean values, and substitute impulse pixel with half of the value of the summation of median and mean value. Experimental results show that the proposed algorithm performs a better noise filtering ability as the images are highly corrupted.","PeriodicalId":338489,"journal":{"name":"2009 International Conference on Future Computer and Communication","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"16","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 International Conference on Future Computer and Communication","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICFCC.2009.87","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 16
Abstract
The progressive switching median (PSM) filter implements a noise detection algorithm before filtering. Both noise detection and filtering procedures are progressively repeated for a number of iterations. As an attempt to improve the PSM filter, an improved progressive switching median filter (IPSM) is proposed to enhance progressive median filter in term of its noise filtering ability. The proposed algorithm sets a limit on the number of good pixels used in determine median and mean values, and substitute impulse pixel with half of the value of the summation of median and mean value. Experimental results show that the proposed algorithm performs a better noise filtering ability as the images are highly corrupted.