中文 | English

 

Calligraphic Beautification of Handwritten Chinese Characters

 

 

Chinese calligraphy and handwritten type of characters play important roles in the life and culture of China. Though, existing tools for calligraphy generation are confined to font-based methods, ignoring individualities of different writers. In this project, SCUT team has exploreed a novel beautification approach for handwritten Chinese characters that is able to beautify user-input handwritings while preserving the users’ individualities. As far as we observe, few researches have been published on the same topic, particularly for Chinese handwriting beautification.

Through study on a number of relating topics, SCUT team propose a patternized approach for handwritten Chinese character beautification and has achieved elementary success. An integrated systematic framework for handwritten Chinese character beautification is proposed for the first time in the literature. SCUT team focus on a patternized approach in attempting beautification of handwritten Chinese characters through feature corresponding and fusing. Simulated Analogous Reasoning Process is employed in the proposed system to adopt some certain styles onto users’ input characters. The system is made applicable by accommodating to common variations in handwritings. The verification-based stroke corresponding algorithm allows inputs that contain connected or falsely-separated strokes. Also, the tri-unit stroke model which handles the connection parts between successive strokes ensures a natural simulation and beautification for the connection parts expressly, and thus better preserves reflections of user individualities. The proposed system is proved to be effective and feasible on transfiguring handwritings and preserving originality of users’ in series of experiments. Exampls is shown in figure 1.

Potential applications of the handwritten Chinese character beautification system include aesthetic handwriting generating, intelligent feed back in Computer-Aided Chinese handwriting learning, generating handwriting samples for classifier training and testing, etc.