{"title":"A novel hierarchical medical image registration method based on multiscale and contour line","authors":"Jinyan Hu, Yunfeng Yang, Z. Su","doi":"10.1109/ICSAI.2012.6223401","DOIUrl":null,"url":null,"abstract":"Medical image registration is the key technology in the modern medical images processing field. A rapid and effective hierarchical registration method of the medical images based on multiscale transform and contour line is proposed in the paper, and it can be accomplished automatically. Firstly, edge features of the couple images are extracted by Canny operator. Then the contour lines of the couple images are extracted based on the edge features. Secondly, Principal Axis method is used to accomplish the rough registration based on the contour lines. Thirdly, multiscale image sets which obtained by a new multiscale transform are used to accomplish the couple images' accurate registration based on the rough registration. Experiment results show that this method not only can achieve more accurate registration results, but also can reduce the computational time greatly. The accurate registration results also can be achieved in the noisy environment.","PeriodicalId":164945,"journal":{"name":"2012 International Conference on Systems and Informatics (ICSAI2012)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 International Conference on Systems and Informatics (ICSAI2012)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSAI.2012.6223401","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
Medical image registration is the key technology in the modern medical images processing field. A rapid and effective hierarchical registration method of the medical images based on multiscale transform and contour line is proposed in the paper, and it can be accomplished automatically. Firstly, edge features of the couple images are extracted by Canny operator. Then the contour lines of the couple images are extracted based on the edge features. Secondly, Principal Axis method is used to accomplish the rough registration based on the contour lines. Thirdly, multiscale image sets which obtained by a new multiscale transform are used to accomplish the couple images' accurate registration based on the rough registration. Experiment results show that this method not only can achieve more accurate registration results, but also can reduce the computational time greatly. The accurate registration results also can be achieved in the noisy environment.