On-line Recognition of Cursive Korean Characters Based on Hidden Markov Model and Level Building


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 3, No. 5, pp. 1281-1293, Sep. 1996
10.3745/KIPSTE.1996.3.5.1281,   PDF Download:

Abstract

In this paper, we propose a novel recognition model of on-line cursive Korean characters using HMM(Hidden Markov Model) and level building algorithm. The model is constructed as a form of recognition network with HMM for graphemes and Korean combination rules. Though the network is so flexible as to accomodate variability of input patterns, it has a problem of recognition speed caused by 11,172 search paths. To settle the problem, we modify the level building algorithm to be adapted directly to the Korean combination rules and apply it to the model. The modified algorithm is efficient network search procedure time complexity of which depends on the number of HMMs for each grapheme, not the number of paths in the extensive recognition network. A test with 15,000 handwritten characters shows recognition rate 90% and speed of 0.72 second per character.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
K. S. Kyoon, K. K. Hyun, L. J. Kook, L. J. Uk, K. H. Joon, "On-line Recognition of Cursive Korean Characters Based on Hidden Markov Model and Level Building," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 3, no. 5, pp. 1281-1293, 1996. DOI: 10.3745/KIPSTE.1996.3.5.1281.

[ACM Style]
Kim Sang Kyoon, Kim Kyung Hyun, Lee Jong Kook, Lee Jae Uk, and Kim Hang Joon. 1996. On-line Recognition of Cursive Korean Characters Based on Hidden Markov Model and Level Building. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 3, 5, (1996), 1281-1293. DOI: 10.3745/KIPSTE.1996.3.5.1281.