{"title":"基于最大曲率流特征点定位的三维几何统计模型","authors":"Hui Yu, Wu Jun-Sheng, Y. Bin, Zhang Chen","doi":"10.1145/3035012.3035016","DOIUrl":null,"url":null,"abstract":"Aiming at the present problem that the spine and the part of the spine lack the sample library of geometric statistical model of different age groups, this paper studies a method to construct the three-dimensional geometric statistic model based on the locating feature points of maximum curvature flow. In this method, the 3D reconstructed human lumbar vertebrae model is adaptively identified and located based on the feature points of the normal curvature maxima, so as to the sample matrix is generated for each model. Then the improved ICP algorithm is used to align and register the sample matrix. Finally, the PCA (Principal Component Analysis) is used to train the model template after registration, in order to get the sample library of geometry statistical model of spine.","PeriodicalId":130142,"journal":{"name":"Proceedings of the 5th International Conference on Bioinformatics and Computational Biology","volume":"116 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Three-dimensional geometric statistical model based on locating feature points of maximal curvature flow\",\"authors\":\"Hui Yu, Wu Jun-Sheng, Y. Bin, Zhang Chen\",\"doi\":\"10.1145/3035012.3035016\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Aiming at the present problem that the spine and the part of the spine lack the sample library of geometric statistical model of different age groups, this paper studies a method to construct the three-dimensional geometric statistic model based on the locating feature points of maximum curvature flow. In this method, the 3D reconstructed human lumbar vertebrae model is adaptively identified and located based on the feature points of the normal curvature maxima, so as to the sample matrix is generated for each model. Then the improved ICP algorithm is used to align and register the sample matrix. Finally, the PCA (Principal Component Analysis) is used to train the model template after registration, in order to get the sample library of geometry statistical model of spine.\",\"PeriodicalId\":130142,\"journal\":{\"name\":\"Proceedings of the 5th International Conference on Bioinformatics and Computational Biology\",\"volume\":\"116 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-01-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 5th International Conference on Bioinformatics and Computational Biology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3035012.3035016\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 5th International Conference on Bioinformatics and Computational Biology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3035012.3035016","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Three-dimensional geometric statistical model based on locating feature points of maximal curvature flow
Aiming at the present problem that the spine and the part of the spine lack the sample library of geometric statistical model of different age groups, this paper studies a method to construct the three-dimensional geometric statistic model based on the locating feature points of maximum curvature flow. In this method, the 3D reconstructed human lumbar vertebrae model is adaptively identified and located based on the feature points of the normal curvature maxima, so as to the sample matrix is generated for each model. Then the improved ICP algorithm is used to align and register the sample matrix. Finally, the PCA (Principal Component Analysis) is used to train the model template after registration, in order to get the sample library of geometry statistical model of spine.