Robot Brush-Writing System of Chinese Calligraphy Characters
In this paper, robot calligraphy systems is developed to write Chinese brush characters dynamically. The BBOD algorithm of stroke extraction is optimized by adding a rule for merging stroke. the results show that the accuracy of stroke extraction is 95% for the Simple-style font, 92% for Kai-style font and 90% for Yan-style font. A model of calligraphy features is established, which includes not only the spatial structure features of Chinese characters, but also the dynamic writing features of Chinese characters. In the period of trajectory planning, a rule of Chinese brush characters applies to optimize the trajectory of stroke, and there are two steps of motion planning, cubic B-spline algorithm is used to plan the Cartesian path, then S curve algorithm is used to plan the joint space trajectory, in order to control manipulator smoothly and stably. To verify the proposed method, three types of experiments are conducted and the developed systems achieved good results in Chinese brush calligraphy reproducing.
KeywordsRobot calligraphy system Stroke extraction Calligraphy feature model Calligraphy writing rule
This work is supported by National Key R&D Program of China (Project No. 2017YFB1300400), National Natural Science Foundation of China (Project No. 61673304) and Wuhan Science and Technology Planning Project (Project No.: 2018010401011275).
- 1.Mueller, S., Huebel, N., Waibel, M., et al.: Robotic calligraphy—learning how to write single strokes of Chinese and Japanese characters. In: 2013 International Conference on Intelligent Robots and Systems (IROS), pp. 1734–1739. Institute of Electrical and Electronics Engineers Inc., Tokyo, Japan (2013)Google Scholar
- 2.Liu, K., Huang, Y.S., Suen, C.Y.: Robust stroke segmentation method for handwritten Chinese character recognition. In: Proceedings of the Fourth International Conference on Document Analysis and Recognition, pp. 211–215. IEEE, Los Alamitos, CA, United States, Ulm, Ger (1997)Google Scholar
- 3.Cao, R., Tan, C.L.: A model of stroke extraction from Chinese character images. In: Proceedings 15th International Conference on Pattern Recognition, IEEE, pp. 4: 368–371. Institute of Electrical and Electronics Engineers Inc., Barcelona, Spain (2000)Google Scholar
- 5.Lyu, P., Bai, X., Yao, C., et al.: Auto-encoder guided GAN for Chinese calligraphy synthesis. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 1095–1100. IEEE Computer Society, Kyoto, Japan (2017)Google Scholar
- 6.Lo, K.W., Kwok, K.W., Wong, S.M., et al.: Brush footprint acquisition and preliminary analysis for Chinese calligraphy using a robot drawing platform. In: 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5183–5188. Institute of Electrical and Electronics Engineers Inc., United States, Beijing, China (2006)Google Scholar
- 7.Li, J., Sun, W., Zhou, M.C., et al.: Teaching a calligraphy robot via a touch screen. In: 2014 IEEE International Conference on Automation Science and Engineering (CASE), pp. 221–226. IEEE Computer Society, Taipei, Taiwan (2014)Google Scholar
- 10.Yang, L., Li, X.: Animating the brush-writing process of Chinese calligraphy characters. In: Eighth IEEE/ACIS International Conference on Computer & Information Science. IEEE, pp. 683–688. IEEE Computer Society, Shanghai, China (2009)Google Scholar
- 11.Shi, F.Z.: Computer-Aided Geometric Design and Non-uniform Rational B-Spline. Higher Education Press, Beijing (2001)Google Scholar
- 12.Perumaal, S., et al.: Synchronized trigonometric S-curve trajectory for jerk-bounded time-optimal pick and place operation. Int. J. Robot. Autom. 27(4), 385 (2012)Google Scholar