Data-driven Handwriting Synthesis in a Conjoined Manner
Tse-Ju Lin1
Xaio-Feng Jian1
1 National Taiwan University
2 University of British Columbia
In Computer Graphics Forum (Proceedings of Pacific Graphics 2015)
A person's handwriting appears differently within a typical range of variations, and the shapes of handwriting characters also show complex interaction with their nearby neighbors. This makes automatic synthesis of handwriting characters and paragraphs very challenging. In this paper, we propose a method for synthesizing handwriting texts according to a writer's handwriting style. The synthesis algorithm is composed by two phases. First, we create the multidimensional morphable models for different characters based on one writer's data. Then, we compute the cursive probability to decide whether each pair of neighboring characters are conjoined together or not. By jointly modeling the handwriting style and conjoined property through a novel trajectory optimization, final handwriting words can be synthesized from a set of collected samples. Furthermore, the paragraphs' layouts are also automatically generated and adjusted according to the writer's style obtained from the same dataset. We demonstrate that our method can successfully synthesize an entire paragraph that mimic a writer's handwriting using his/her collected handwriting samples.
technical paper
presentation slide

@article{ ChenLJSC:2015,
     author = {Hsin-I Chen and Tse-Ju Lin and Xiao-Feng Jian and I-Chao Shen and Bing-Yu Chen},
     journal = {Computer Graphics Forum},
     title = {Data-driven Handwriting Synthesis in a Conjoined Manner},
     year = {2015},
     volume = {34},
     number = {7},
     pages = {235-244},
     note = {(Pacific Graphics 2015 Conference Proceedings)}
1504 visitors since August 2013