Adaptive post-processing of OCR text via knowledge acquisition
Lon‐Mu Liu, Yair M. Babad, Wei Sun, Ki-Kan Chan · 1991
According to Wikipedia, Optical Character Recognition (OCR) “is the mechanical or electronic translation of images of handwritten or typewritten text (usually captured by a scanner) into machine-editable text. ” Even though a lot of academic research has been carried out on this topic, there are still needs for improving the accuracy and completeness of the scanned text. More specifically, scanned documents are prone to inaccuracy and error. This is especially true with large amounts of aged books in libraries across the country. Our group plans on creating a solution which will help to reduce some of these errors in scanned documents. 2. Related work