On-Line Cursive Korean Character Recognition by using Curvature Models

Chang-Soo Kim, Missouri University of Science and Technology
Byung Hwan Jun
Moo Young Kim
Woo Seong Kim
Jaihie Kim

This document has been relocated to http://scholarsmine.mst.edu/ele_comeng_facwork/1795

There were 3 downloads as of 28 Jun 2016.


A cursive Korean character consists of several Korean alphabets where connection is present within and among the alphabets. Recognition of Korean characters can be carried out by splitting each character into smaller primitives. Small line segments can be used as the primitives. But this approach requires too much processing time, for there can be many candidate references to be matched to one input character and each reference usually consists of too many primitives. In this paper, we propose an approach using structural curvature models to overcome the difficulties of using small line segments. These models are obtained by segmenting the input character at the points showing sudden change in direction, excessive rotation, etc. By doing this, rather larger and structural curve segments can be used as the basic primitives to be matched resulting in the savings of processing time and better recognition rate