• Informatization Policy
• /
• v.19 no.3
• /
• pp.50-63
• /
• 2012

This thesis is designed to analyze how the search for Chinese ideographs is done in Koreanology-related domestic databases, domestic library databases, domestic academic databases, and overseas library databases, with a view to identifying problems and suggesting solutions to them. The major reasons that impede Chinese ideographs search in Unicode are classified as 'multicode characters', 'simplified characters', and 'variant characters', and three characters are chosen as samples to describe the current practice. Thirteen Koreanology-related databases, five domestic library databases, five domestic academic databases and two overseas library databases are analyzed in terms of Chinese ideographs search. To support search for multicode characters, the open source of the Unicode consortium must be applied. To improve search for simplified and variant characters, a matching table must be standardized and proposed to the Unicode consortium.

• Journal of KIISE:Software and Applications
• /
• v.36 no.9
• /
• pp.683-690
• /
• 2009

One of the major problems that prevent us from building a good recognition system for large-scale on-line Chinese character recognition using HMMs is increasing recognition time. In this paper, we propose a clustering method to solve recognition speed problem and an efficient distance measure between HMMs. From the experiments, we got about twice the recognition speed and 95.37% 10-candidate recognition accuracy, which is only 0.9% decrease, for 20,902 Chinese characters defined in Unicode CJK unified ideographs.