{"title":"Automatic Georeferencing of Map Images Using Unsupervised Learning and Graph Analysis","authors":"Enrique Arriaga-Varela, Toru Takahashi","doi":"10.52591/lxai202012129","DOIUrl":null,"url":null,"abstract":"We present a novel method for the automatic georeferencing of heterogeneous map images based on the analysis of the spatial relationships between their lines of text and the geographical locations they depict. Our approach differs from previous work in that the only input provided is the raster image, as it does not require additional hints or metadata. The method is also designed to be highly tolerant of maps with different art styles, scales, orientations, and cartographic projections. To accomplish this task, we leverage the power of modern OCR (Optical Character Recognition) and geocoding services to generate a series of candidate ground control points (GCP) and then discriminate between them using a combination of clustering algorithms and graph analysis. Experimental results for 359 map images demonstrate the viability of the proposed method. We achieved a precision ranging from 81.19% to 97.56% and a recall from 55.71% to 71.15%.","PeriodicalId":301818,"journal":{"name":"LatinX in AI at Neural Information Processing Systems Conference 2020","volume":"248 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"LatinX in AI at Neural Information Processing Systems Conference 2020","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.52591/lxai202012129","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
We present a novel method for the automatic georeferencing of heterogeneous map images based on the analysis of the spatial relationships between their lines of text and the geographical locations they depict. Our approach differs from previous work in that the only input provided is the raster image, as it does not require additional hints or metadata. The method is also designed to be highly tolerant of maps with different art styles, scales, orientations, and cartographic projections. To accomplish this task, we leverage the power of modern OCR (Optical Character Recognition) and geocoding services to generate a series of candidate ground control points (GCP) and then discriminate between them using a combination of clustering algorithms and graph analysis. Experimental results for 359 map images demonstrate the viability of the proposed method. We achieved a precision ranging from 81.19% to 97.56% and a recall from 55.71% to 71.15%.