{"title":"Rotational invariant image matching based on phase only correlation","authors":"A. Şengur, M. Karabatak","doi":"10.1109/SIU.2010.5653488","DOIUrl":null,"url":null,"abstract":"In this work, a rotational invariant image template matching method based on log-polar transform and phase only correlation is presented. The method is composed of two stages. While applying the 2nd Hanning window is formed the first stage, several steps, for phase-based rotational image template matching constitutes the second stage. MATLAB is used for computer simulations. We cropped various image templates for matching purposes. We then rotated that template images with 15, 30 45, 60 and 75 degrees respectively and we saved them. Thus, we obtained totally 60 images for 10 different template images. We finally obtained 93.33% matching accuracy.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE 18th Signal Processing and Communications Applications Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIU.2010.5653488","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this work, a rotational invariant image template matching method based on log-polar transform and phase only correlation is presented. The method is composed of two stages. While applying the 2nd Hanning window is formed the first stage, several steps, for phase-based rotational image template matching constitutes the second stage. MATLAB is used for computer simulations. We cropped various image templates for matching purposes. We then rotated that template images with 15, 30 45, 60 and 75 degrees respectively and we saved them. Thus, we obtained totally 60 images for 10 different template images. We finally obtained 93.33% matching accuracy.