{"title":"Computing principal direction fields as frame bundle cross sections","authors":"P. Sander, S. Zucker","doi":"10.1109/ICPR.1988.28298","DOIUrl":null,"url":null,"abstract":"Essential information about the differential structure of smooth surfaces is embodied in their principal curvature and principal direction fields. A particular type of fibre bundle, a frame bundle, is defined over estimated surface trace points and the computation of these fields is presented as the determination of the appropriate cross section through the frame bundle. Any approach to the recovery of surface structure must deal with the inherent limitations of local computations-an iterative constraint-satisfaction process is developed for the reliable extraction of the principal-direction cross section. Present methods are applied to the synthetic images corrupted by noise and to magnetic resonance imagery.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"[1988 Proceedings] 9th International Conference on Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICPR.1988.28298","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
Essential information about the differential structure of smooth surfaces is embodied in their principal curvature and principal direction fields. A particular type of fibre bundle, a frame bundle, is defined over estimated surface trace points and the computation of these fields is presented as the determination of the appropriate cross section through the frame bundle. Any approach to the recovery of surface structure must deal with the inherent limitations of local computations-an iterative constraint-satisfaction process is developed for the reliable extraction of the principal-direction cross section. Present methods are applied to the synthetic images corrupted by noise and to magnetic resonance imagery.<>