LEADER 03443nam 2200769 a 450 001 996217845303316 005 20230829005320.0 010 $a1-280-84569-4 010 $a9786610845699 010 $a0-19-152544-8 010 $a1-4356-2116-6 035 $a(CKB)1000000000375220 035 $a(EBL)716795 035 $a(OCoLC)271577589 035 $a(SSID)ssj0000087438 035 $a(PQKBManifestationID)11126369 035 $a(PQKBTitleCode)TC0000087438 035 $a(PQKBWorkID)10053187 035 $a(PQKB)10287622 035 $a(StDuBDS)EDZ0000073775 035 $a(MiAaPQ)EBC716795 035 $a(MiAaPQ)EBC7035320 035 $a(Au-PeEL)EBL7035320 035 $a(EXLCZ)991000000000375220 100 $a20060712d2006 uy 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 10$aImage to interpretation$b[electronic resource] $ean intelligent system to aid historians in reading the Vindolanda texts /$fMelissa M. Terras ; with a foreword by Alan K. Bowman and Michael Brady 210 $aOxford $cOxford University Press$d2006 215 $a1 online resource (265 p.) 225 1 $aOxford studies in ancient documents 300 $a"Chapters 4, 5, and Appendix A co-authored with Paul Robertson." 311 $a0-19-170812-7 311 $a0-19-920455-1 320 $aIncludes bibliographical references (p. [231]-247) and index. 327 $aContents; List of Tables; 1. Introduction; I: Knowledge Elicitation and the Papyrologist; II: Image to Interpretation; Appendix A. Using a Stochastic MDL Architecture to Read the Vindolanda Texts; Appendix B. Annotation; Appendix C. Vindolanda Letter Forms Corpus; References; Index 330 $aThe ink and stylus tablets discovered at the Roman fort of Vindolanda are a unique resource for scholars of ancient history. However, the stylus tablets in particular are extremely difficult to read. This book details the development of what appears to be the first system constructed to aid experts in the process of reading an ancient document, exploring the extent to which techniques from Artificial Intelligence can be used to develop a system that could aid historians in readingthe stylus texts. Image to Interpretation includes a model of how experts read ancient texts, a corpora of letter f 410 0$aOxford studies in ancient documents. 606 $aInscriptions, Latin$zEngland$zChesterholme 606 $aWooden tablets$zEngland$zChesterholme 606 $aPaleography$xData processing 606 $aArtificial intelligence$xResearch 606 $aConnectionism 606 $aMinimum description length (Information theory) 606 $aImage analysis 607 $aVindolanda Site (Chesterholme, England) 607 $aChesterholme (England)$xAntiquities, Roman 615 0$aInscriptions, Latin 615 0$aWooden tablets 615 0$aPaleography$xData processing. 615 0$aArtificial intelligence$xResearch. 615 0$aConnectionism. 615 0$aMinimum description length (Information theory) 615 0$aImage analysis. 676 $a936.2/881 700 $aTerras$b Melissa M$0855887 701 $aRobertson$b Paul$f1956-$01015623 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a996217845303316 996 $aImage to interpretation$92372320 997 $aUNISA