원문정보
초록
영어
Through the analysis on the unique characteristics of Uyghur characters, in order to further improve the recognition rate, this paper developed the Center Distance Feature (CDF) to its modified form which is named as Modified Center Distance Feature (MCDF). By combination with some low dimensional features including stroke number feature, additional part’s location feature, shape feature, bottom-up and left-right density feature(BULR) in experiments, MCDF gifted robust recognition accuracy of 98.77% for the 32 isolated forms of Uyghur characters. MCDF increased the recognition accuracy by 4.51 points comparing with the result from the combination of CDF with the same low dimensional features mentioned above, which is 94.16%. This paper used the samples from 400 different volunteers. The recognition system is trained using 70 percent of 12800 samples from 400 different writers and tested on the remained 30 percent.
목차
1. Introduction
2. On-line handwritten character recognition system
3. Related Work
4. Feature Extraction Algorithm
4.1. Center Distance Feature-CDF with its Three Different Implementations (CDF-2, CDF-4 and CDF-8)
4.2. Modified Center Distance Feature-MCDF and its Comparison with Center Distance Feature-CDF)
4.3. Stroke Number Feature
4.4. Additional Part’s Location Feature
4.5. Bottom-Up (BUDR) and Left-Right (LRDR) Density Ratio
4.6. Shape Feature of Additional Strokes
5. Experimental Results and Analysis
5.1 Experimental Results and Facts
5.2 Analysis on the Experimental Facts
6. Conclusions
Acknowledgements
References