SIG/AH-MANAGING TEXT WITH SCANNING, OCR, AND TEXT ORIENTED RETRIEVAL SYSTEMS

摘要

The scarcity of machine readable text has curbed the speed with which the humanities have entered the information age. To pursue their research, archivists, historians, and literary scholars usually require large corpora. The philosopher's stone for today's computer literate humanist would have the power to convert book based text to a machine readable form, thereby allowing computer indexing, searching, and analysis. A number of universities have supported scanning facilities for conversion of print to binary form, but generally scanners and OCR approaches have been, at best, time consuming and labor intensive. New scanning technology, however, offers promise. Panelists will discuss the evaluation of scanners and OCR equipment software and services, as well as the software necessary to manage the resulting unstructured files that result.