{"title":"结合几何不变量和模糊聚类进行目标识别","authors":"E. Walker","doi":"10.1109/NAFIPS.1999.781758","DOIUrl":null,"url":null,"abstract":"Object recognition is the process of identifying the types and locations of objects in the image. Earlier work has shown the desirability of using fuzzy compatibility for local feature correspondence and fuzzy clustering for pose estimation of two dimensional objects. The paper extends the methodology to images of three dimensional objects by applying geometric invariants, specifically the cross ratio of four collinear points. The recognition process is divided into three subtasks: local feature correspondence, object identification, and pose determination. Algorithms are described for each subtask.","PeriodicalId":335957,"journal":{"name":"18th International Conference of the North American Fuzzy Information Processing Society - NAFIPS (Cat. No.99TH8397)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1999-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Combining geometric invariants with fuzzy clustering for object recognition\",\"authors\":\"E. Walker\",\"doi\":\"10.1109/NAFIPS.1999.781758\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Object recognition is the process of identifying the types and locations of objects in the image. Earlier work has shown the desirability of using fuzzy compatibility for local feature correspondence and fuzzy clustering for pose estimation of two dimensional objects. The paper extends the methodology to images of three dimensional objects by applying geometric invariants, specifically the cross ratio of four collinear points. The recognition process is divided into three subtasks: local feature correspondence, object identification, and pose determination. Algorithms are described for each subtask.\",\"PeriodicalId\":335957,\"journal\":{\"name\":\"18th International Conference of the North American Fuzzy Information Processing Society - NAFIPS (Cat. No.99TH8397)\",\"volume\":\"15 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1999-06-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"18th International Conference of the North American Fuzzy Information Processing Society - NAFIPS (Cat. No.99TH8397)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NAFIPS.1999.781758\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"18th International Conference of the North American Fuzzy Information Processing Society - NAFIPS (Cat. No.99TH8397)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NAFIPS.1999.781758","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Combining geometric invariants with fuzzy clustering for object recognition
Object recognition is the process of identifying the types and locations of objects in the image. Earlier work has shown the desirability of using fuzzy compatibility for local feature correspondence and fuzzy clustering for pose estimation of two dimensional objects. The paper extends the methodology to images of three dimensional objects by applying geometric invariants, specifically the cross ratio of four collinear points. The recognition process is divided into three subtasks: local feature correspondence, object identification, and pose determination. Algorithms are described for each subtask.