B.-J. Cho, B.-K. Sin, and S.-U. Kim (Korea)
P2DHMM, keyword, spotting, character, model, synthesis
We propose a new method of dynamically synthesizing Korean Hangul character image templates and then converting them into P2DHMMs in real time. Unlike the left-to-right linear concatenation of letters in English words, the nonlinear, 2D composition of letter models in Hangul is not straightforward and has not been tried for machine-print character recognition. Without doubt, the proposed method of character modeling is more advantageous than whole word HMMs in regard to the memory requirement as well as the training difficulty. In the proposed method individual character models are synthesized in real-time using the trained grapheme image templates. The proposed method has been applied to key character/word spotting in document images. In a series of preliminary experiments, we observed the performance of 80% and 67% in Hangul character and word spotting respectively without language models. This performance, we believe, is adequate and the proposed method is effective for the real time applications.
Important Links:
Go Back
