{"title":"Quaternion linear colour edge-sharpening filter using genetic algorithm","authors":"Shagufta Yasmin, S. Sangwine","doi":"10.1109/CEEC.2016.7835900","DOIUrl":null,"url":null,"abstract":"A quaternion linear colour edge-sharpening filter is presented. A quaternion convolution mask is created using a genetic algorithm (GA) and a zooming technique. When the new filter is applied to colour images, it produces sharpened colour edges in all directions in regions where colour (but not intensity) edges occur in the image. The methodology of the proposed filter depends on the zooming technique and fitness function. The new filter is tested on different kind of colour images and the experimental results show that the proposed scheme is needed for sharpening colour edges in all directions with only one mask. This proposed filter is a great achievement for developing linear colour vector image filters because it is difficult to design manually/mathematically. This new filter is an example of a linear colour vector image filter developed using genetic algorithm and zooming techniques.","PeriodicalId":114518,"journal":{"name":"2016 8th Computer Science and Electronic Engineering (CEEC)","volume":"210 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 8th Computer Science and Electronic Engineering (CEEC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CEEC.2016.7835900","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
A quaternion linear colour edge-sharpening filter is presented. A quaternion convolution mask is created using a genetic algorithm (GA) and a zooming technique. When the new filter is applied to colour images, it produces sharpened colour edges in all directions in regions where colour (but not intensity) edges occur in the image. The methodology of the proposed filter depends on the zooming technique and fitness function. The new filter is tested on different kind of colour images and the experimental results show that the proposed scheme is needed for sharpening colour edges in all directions with only one mask. This proposed filter is a great achievement for developing linear colour vector image filters because it is difficult to design manually/mathematically. This new filter is an example of a linear colour vector image filter developed using genetic algorithm and zooming techniques.