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.
|Title of host publication||Proceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995|
|Publisher||IEEE Computer Society|
|Number of pages||4|
|Publication status||Published - 1995|
|Event||3rd International Conference on Document Analysis and Recognition, ICDAR 1995 - Montreal, Canada|
Duration: 1995 Aug 14 → 1995 Aug 16
|Name||Proceedings of the International Conference on Document Analysis and Recognition, ICDAR|
|Conference||3rd International Conference on Document Analysis and Recognition, ICDAR 1995|
|Period||95/8/14 → 95/8/16|
Bibliographical notePublisher Copyright:
© 1995 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition