Example-based Chinese Calligraphy Synthesis
Chinese calligraphy synthesis is important meaningful to protect non-heritage cultural and augmented reality.In this paper,we proposed an algorithm of Chinese Calligraphy synthesis based on examples.First,we construct a stroke library represented by vector.Second,we obtain the trajectory of character stroke from the digital tablet input,and match the most similar character stroke from the stroke library and replace the trajectory with it.Third,we evaluate the style using recurrent neural networks(RNNs).We also propose a new model to describe Chinese character topology by 9-intersections & range relation(9IRR)according to experience.Finally,we employ simulated annealing strategy to optimize the Chinese character topology with aesthetic requirements.Experimental results show that character shapes generated are visual pleasing.
Chinese calligraphy synthesis Chinese character topology recurrent neural networks optimization
Wei Li Yumin Chen Chao Tang Shaoyong Yu
School of Computer and Information Engineering,Xiamen University of Technology,China Department of Computer Science and Technology,Hefei University,China
国际会议
深圳
英文
253-256
2018-01-21（万方平台首次上网日期，不代表论文的发表时间）