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

We propose a new method for o!-line recognition of unconstrained handwritten words consisting of Korean and numeric characters. To overcome the di$culty in separating touching characters, we adopt an over-segmentation strategy. Given a slice of the input word image, we "nd the optimal segment combination using a lexicon-driven word scoring technique and a nearest-neighbor classi"er. The optimal combination gives the "nal segmentation positions for individual characters, along with the best matching word in the lexicon. Superiority of the proposed system has been proven by testing it with 908 images of unconstrained words handwritten on live mail pieces. 2001 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.