CCD-BSMG: Composite-Curve-Dilation-Based Brush Stroke Model Generator for Robotic Chinese Calligraphy

Brush stroke training models for Chinese brush play an important role in robotic Chinese calligraphy as the basis of stroke generation. How to combine the end-to-end method and physical model needs to be further clarified. As a large number of brush strokes collected by robotic arm for learning and training lacks operability. The simulated brush stroke model can be used as a source of training datasets for deep learning and training instead of real samples collected by robot. With different combinations of physical parameters of the robotic arm, a sufficient amount of sample data can be generated by the simulated brush stroke model and then to train a generator based on the datasets. In this way, we propose a composite-curve-dilation brush stroke model generator (CCD-BSMG) based on our composite-curve-dilation brush stroke model (CCD-BSM), which was formed by composite curve and morphological dilation directly according to the physical parameters of robotic arm and writing posture of the brush without a large number of samples for parameter estimation. The CCD-BSMG can generate the graphics with the dataset simulated by CCD-BSM for deep learning and training. Furthermore, with the output parameters of CCD-BSMG, the images reconstructed by robotic arm can have a better performance. Compared with other stroke generative models based on disordered pixels, our generator is based on parameterized brush strokes and provides a better foundation for robotic writing in deep learning or other fields. Compared with existing model and real stroke graphics written by robots, the results of several experiments prove that the proposed CCD-BSMG can generate stroke graphics well and show that it outperformed state-of-the-art stroke models. The results demonstrate the advantages of our proposed model in terms of high similarity and especially show the robustness and efficacy.