Title :
Off-line recognition of Korean scripts using distance matching and neural network classifiers
Author :
Kim, Soo Hyung ; Doh, Jeong-In
Author_Institution :
Multimedia Center, Samsung Electron. Co. Ltd., Kyungki, South Korea
Abstract :
An off-line recognition engine is proposed for handwritten Korean characters based on a distance matching and the neural network technique. The distance matching selects a set of several candidates from the large set of character classes, and the neural network performs a detailed classification on the candidates. As an approach for combining the two methodologies, a clustering method based on sample distributions has been devised. Recognition accuracy of the engine on a public database, PE92, is 84.1%. About four character patterns can be processed in a second on PC
Keywords :
character recognition; character sets; document image processing; image matching; microcomputer applications; neural nets; Korean scripts; PC; PE92 public database; character classes; character patterns; clustering method; distance matching; handwritten Korean characters; neural network classifiers; off-line recognition engine; recognition accuracy; sample distributions; Character recognition; Clustering methods; Databases; Electronic mail; Engines; Handwriting recognition; Image segmentation; Neural networks; Pattern recognition; Pixel;
Conference_Titel :
Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-8186-7128-9
DOI :
10.1109/ICDAR.1995.598938
