Automatic Training Set Generation for Better Historic Document Transcription and Compression

The more complete the training set of an optical character recognition platform, the greater the chances of obtaining a better precision in transcription. The development of a database for such purpose is a task of paramount effort as it is performed manually and must be as extensive as possible in order to potentially cover all words in a language. Dealing with historic documents either handwritten, typed, or printed is even a harder effort as documents are often degraded by time and storage conditions. The recent work of Silva-Lins showed how to automatically generate training sets of isolated characters for cursive writing of one specific person. This is particularly important in the transcription of historic files of important people. The present work improves that strategy by analyzing letter ligature patterns. The improvement in OCR transcription accuracy both of printed, typed and handwritten documents is borne out by experimental evidence.