On the relationship of the Markov mesh to the NSHP Markov chain
Pattern Recognition Letters
The State of the Art in Online Handwriting Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keyword Spotting in Poorly Printed Documents using Pseudo 2-D Hidden Markov Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
2-D HMM methods have recently been applied to handwritten Chinese character recognition(HCCR) with much practical prospect, however, the time consuming is a great obstacle for its widely using. To overcome this weakness a novel block-based ICM algorithm, which will decode image block by block other than pixel by pixel, is proposed. Experiments shows that it can work much better than the traditional one for HCCR with a little higher accuracy and much higher speed of recognition. It offers a great potential for HCCR when using truly-2D HMM.