User-assisted OCR enhancement for digital archive construction
J. He · 2005
The creation of structured digital libraries from paper-based archives is an area of growing demand in many scientific and cultural fields, and is not satisfied either by off-the-shelf OCR or commercial form-processing systems. This paper describes the configurable image analysis and text post-processing tools required to augment a standard OCR system to meet digital archiving requirements. Evaluation results are summarised for a prototype system currently being used by the UK Natural History Museum to convert a Lepidoptera card index of more than 500,000 cards to a searchable digital archive.