A Moving Window Classifier for Off-line Character Recognition

CHARACTER RECOGNITION M. S. HOQUE, M. C. FAIRHURST Electronic Engineering Laboratory, University of Kent, Canterbury, Kent CT2 7NT, United Kingdom. E-mail: fmsh4,[email protected] A new classi cation scheme, primarily aimed at applications in document image processing, is presented. Features are extracted from a partial image and a subclassi er generates scores based on the likelihood of the sub-image belonging to the candidate classes. This partial classi cation is carried out for several overlapping image segments and scores are combined to make the nal classi cation. The scheme shows promising results in OCR applications where high processing speeds are achievable with minimal compromise in the recognition accuracy.