Yalniz, I. Z.Altingovde, I. S.Güdükbay, UğurUlusoy, Özgür2016-02-082016-02-082009-121556-4673http://hdl.handle.net/11693/22511This article presents Ottoman Archives Explorer, a Content-Based Retrieval (CBR) system based on character recognition for printed and handwritten historical documents. Several methods for character segmentation and recognition stages are investigated. In particular, sliding-window and histogram segmentation methods are coupled with recognition approaches using spatial features, neural networks, and a graph-based model. The prototype system provides CBR of document images using both example-based queries and a virtual keyboard to construct query words. © 2009 ACM.EnglishContent-based retrieval (CBR)Historical document analysisInformation retrieval (IR)Optical character recognition (OCR)CBRCharacter segmentationConstruct queriesGraph-based modelingHistogram segmentationHistorical documentsRetrieval systemsGraphic methodsHistoryOptical character recognitionQuery processingSearch enginesArticle10.1145/1658346.16583481556-4711