Automatic Generation of Artistic Chinese Calligraphy

  • Authors:
  • Songhua Xu;Francis C. M. Lau;William K. Cheung;Yunhe Pan

  • Affiliations:
  • Zhejiang University;University of Hong Kong;Hong Kong Baptist University;Zhejiang University

  • Venue:
  • IEEE Intelligent Systems
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

This intelligent system can automatically generate new Chinese calligraphy artwork to meet visually aesthetic requirements. The system first extracts the hierarchical parametric representations of Chinese characters from input images of existing calligraphic style to form a compact set of training examples. The extraction results are stored in a small structural stroke database and then exploited to form a continuous calligraphy knowledge space. The space is spanned by character examples of different styles (knowledge sources), which are aggregated and aligned according to a proposed constraint-based analogous-reasoning process. By incorporating a set of simple, yet effective geometric constraints, this system can generate novel calligraphic styles that are aesthetically appealing. Samples of novel calligraphic art produced using the system demonstrate the approach's effectiveness.