Improving Chinese handwriting Recognition by Fusing speech recognition
Improving Chinese handwriting Recognition by Fusing speech recognition Zhang Xi-Wen CSE, CUHK and HCI Lab. , ISCAS 2005. 4. 12
Outline • • 1 Chinese handwriting recognition 2 Chinese speech recognition 3 Information fusion 4 Experimental results
1. Handwriting Recognition • Handwriting segmentation • Character recognition
1. 1 Handwriting segmentation • It is more difficult for Chinese handwriting segmentation
Character extraction using histogram • A histogram of between-stroke gaps. • The dimidiate threshold of the histogram is to extract lines of strokes. • The dimidiate threshold of the histogram of a line of strokes is to extract characters.
Figure 1. Handwriting segmentation
Problems remained • A Chinese character may be mis-segmented into many characters. • Many Chinese characters may be misgrouped as a character. • The segmentation error will inevitably result in handwriting recognition errors.
1. 2 Character recognition – Isolated character recognizer from HW – Many candidates
Handwriting. Text recognized from the handwriting. The ground-truth text. Figure 2. Handwriting recognition
2 Speech recognition • Chinese speech. • On-line, microphone. • Continuous speech recognizer from MS.
Text recognized from the speech corresponding to the handwriting. The ground-truth text. Figure 3. Speech recognition
3 Text fusion • An optimization problem • Dynamic Programming
3. 1 Principles • The fused text should contain more semantic information. • Construct a text with the least characters and the most semantic information.
3. 2 Four ways Text recognized from the handwriting. Text recognized from the speech corresponding to the handwriting. Figure 4. Texts to be fused
3. 3 Dynamic Programming • A directed graph. • Optimal paths.
Figure 5. A directed graph with N levels.
(a) Text recognized from the handwriting. (b) Text recognized from the speech corresponding to the handwriting. (c) The optimal fused text corresponding to the optimal path. (d) The ground-truth text. Figure 6. Text fusion using DP.
3. 4 A language model • Lexicon • Syntax • Semantic
Lexicon
4 Experimental results
• Thank you very much for • your criticism, comments and suggestions! • Email: xwzhang@cse. cuhk. edu. hk • Tel: 3163 -4260
- Slides: 24