Sh. Kim et al., A lexicon-driven approach for optimal segment combination in off-line recognition of unconstrained handwritten Korean words, PATT RECOG, 34(7), 2001, pp. 1437-1447
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.