Page - 104 - in Document Image Processing

J. Imaging 2018,4, 43 2.2. KhmerPalmLeafManuscripts—Collection fromCambodia 2.2.1.Corpus InCambodia,Khmerpalmleafmanuscripts (Figure2)arestill seen inBuddhistestablishments andare traditionallyusedbymonksasreadingscriptures.Various librariesandinstitutionshavebeen collectinganddigitizingthesemanuscriptsandhaveevensharedthedigital imageswith thepublic. For instance, theÉcoleFrançaised’Extrême-Orient (EFEO)has launchedanonlinedatabase (http: //khmermanuscripts.efeo.fr) [20]ofmicrofilmimagesofhundredsofKhmerpalmleafmanuscript collections. SomedigitizedcollectionsarealsoobtainedfromtheBuddhist Institute,whichisoneofthe biggest institutes inCambodiaresponsible for researchonCambodian literatureandlanguagerelated toBuddhism,andalso fromtheNationalLibrary (situated in thecapital city,PhnomPenh),which ishometoa largecollectionofpalmleafmanuscripts.Moreover,astandarddigitizationcampaign wasconducted inorder tocollectpalmleafmanuscript images foundinBuddhist temples indifferent locations throughoutCambodia: PhnomPenh,Kandal,andSiemReap[21]. Figure2.Khmerpalmleafmanuscript. 2.2.2.KhmerScriptandLanguage According to the eraduringwhich thedocumentswere created, slightlydifferentversionsof Khmercharactersareused in thewritingofKhmerpalmleafmanuscripts. TheKhmeralphabet is famousfor itsnumeroussymbols (~70), includingconsonants,different typesofvowels,diacritics,and special characters.Certainsymbolsevenhavemultipleshapesandformsdependingonwhatother symbolsarecombinedwith themtocreatewords. The languageswrittenonpalmleafdocumentsvary fromKhmer, theofficial languageofCambodia, toPali andSanskrit, bywhich themodernKhmer languagewasconsiderably influenced.OnlyaminorityofCambodianpeople, suchasphilologists andBuddhistmonks,areable toreadandunderstandthe latter languages. 2.3. SundanesePalmLeafManuscripts—Collection fromWest Java, Indonesia 2.3.1.Corpus The collection of Sundanese palm leafmanuscripts (Figure 3) comes from Situs Kabuyutan Ciburuy,Garut,West Java, Indonesia. TheKabuyutanCiburuy isacomplexculturalheritage from PrabuSiliwangiandPrabuKianSantang,thekingandthesonofthePadjadjarankingdom.Thecultural complex consists of six buildings. One of them is Bale Padaleuman, which is used to store the Sundanesepalmleafmanuscripts. TheoldestSundanesepalmleafmanuscript inSitusKabuyutan Ciburuy came from the 15th century. In Bale Padaleuman, there are 27 collections of Sundanese manuscripts. Eachcollectioncontains15to30pages,withdimensionsof25–45cminlength×10–15cm inwidth[22]. 2.3.2. SundaneseScriptandLanguage TheSundanesepalmleafmanuscriptswerewritten in theancientSundanese languageandscript. Thecharactersconsistofnumbers,vowels (suchasa, i,u, e, ando),basiccharacters (suchasha,na, 104