A lexicon-driven approach for optimal segment combination in off-line recognition of unconstrained handwritten Korean words

We propose a new method for off-line recognition of unconstrained handwritt en words consisting of Korean and numeric characters. To overcome the diffi culty in separating touching characters, we adopt an over-segmentation stra tegy. Given a slice of the input word image, we find the optimal segment co mbination using a lexicon-driven word scoring technique and a nearest-neigh bor classifier. The optimal combination gives the final segmentation positi ons for individual characters, along with the best matching word in the lex icon. Superiority of the proposed system has been proven by testing it with 908 images of unconstrained words handwritten on live mail pieces. (C) 200 1 Pattern Recognition Society. Published by Elsevier Science Ltd. All right s reserved.