MACHINE-PRINTED CHARACTER-RECOGNITION REVISITED - RE-APPLICATION OF RECENT ADVANCES IN HANDWRITTEN CHARACTER-RECOGNITION RESEARCH

The increasing automation of document processing applications has emph asised the need for robust and reliable recognition of machine-printed characters. Although research in character recognition is now focused principally on applications in reading handwritten characters, this p aper demonstrates how recent progress in the area of multiple-expert c lassification can be exploited to provide new approaches to the proces sing of printed data. Established classification algorithms have been used in a new multiple-expert framework to generate an optimised decis ion combination platform comprising multiple experts, and significant improvements in overall recognition performance on machine-printed cha racters have been achieved. (C) 1998 Elsevier Science B.V. All rights reserved.