{"title":"利用纹理和光谱特征分割地形图像","authors":"D. Mason","doi":"10.1049/IJ-CDT:19790055","DOIUrl":null,"url":null,"abstract":"A method is presented for the segmentation of serial photographs of terrain on the basis of textural as well as spectral characteristics. The method addresses the problems of determining an optimum texture window size, avoiding misclassified areas near region boundaries (owing to the texture window overlapping two or more regions), and coping with textured and untextured regions co-existing in the same scene. The technique is illustrated by an example.","PeriodicalId":344610,"journal":{"name":"Iee Journal on Computers and Digital Techniques","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1979-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"Segmentation of terrain images using textural and spectral characteristics\",\"authors\":\"D. Mason\",\"doi\":\"10.1049/IJ-CDT:19790055\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A method is presented for the segmentation of serial photographs of terrain on the basis of textural as well as spectral characteristics. The method addresses the problems of determining an optimum texture window size, avoiding misclassified areas near region boundaries (owing to the texture window overlapping two or more regions), and coping with textured and untextured regions co-existing in the same scene. The technique is illustrated by an example.\",\"PeriodicalId\":344610,\"journal\":{\"name\":\"Iee Journal on Computers and Digital Techniques\",\"volume\":\"17 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1979-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Iee Journal on Computers and Digital Techniques\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1049/IJ-CDT:19790055\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iee Journal on Computers and Digital Techniques","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1049/IJ-CDT:19790055","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Segmentation of terrain images using textural and spectral characteristics
A method is presented for the segmentation of serial photographs of terrain on the basis of textural as well as spectral characteristics. The method addresses the problems of determining an optimum texture window size, avoiding misclassified areas near region boundaries (owing to the texture window overlapping two or more regions), and coping with textured and untextured regions co-existing in the same scene. The technique is illustrated by an example.