T. Debroutelle, A. Chetouani, S. Treuillet, M. Exbrayat, S. Jesset
{"title":"Classification of friezes engraved on ceramic sherds from 3D scans","authors":"T. Debroutelle, A. Chetouani, S. Treuillet, M. Exbrayat, S. Jesset","doi":"10.1109/ISSPIT.2016.7886038","DOIUrl":null,"url":null,"abstract":"A large corpus of ceramic sherds dating from High Middle Ages has been extracted in Saran (France). The sherds have an engraved frieze made by the potter with a carved wooden wheel, used as a dating to study the dissemination of productions. ARCADIA project aims to develop an automatic classification of this archaeological heritage. The sherds are scanned using a 3D laser scanner. Then, a binary pattern is extracted after projecting the 3D point cloud into a depth map. Gabor filters and bag-of-words are compared as inputs for training a SVM classifier by selecting the pattern as a region of interest. On a database of 377 representative sherds, the recognition rates are about 74% on binary patterns extracted from the 3D scans. Even if the recognition remains below that obtained with manual stampings carried out by the archaeologist, he already saves a lot of time in archiving.","PeriodicalId":371691,"journal":{"name":"2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISSPIT.2016.7886038","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
A large corpus of ceramic sherds dating from High Middle Ages has been extracted in Saran (France). The sherds have an engraved frieze made by the potter with a carved wooden wheel, used as a dating to study the dissemination of productions. ARCADIA project aims to develop an automatic classification of this archaeological heritage. The sherds are scanned using a 3D laser scanner. Then, a binary pattern is extracted after projecting the 3D point cloud into a depth map. Gabor filters and bag-of-words are compared as inputs for training a SVM classifier by selecting the pattern as a region of interest. On a database of 377 representative sherds, the recognition rates are about 74% on binary patterns extracted from the 3D scans. Even if the recognition remains below that obtained with manual stampings carried out by the archaeologist, he already saves a lot of time in archiving.