Automatic Artistic Calligraphy Generation
Songhua Xu, Francis C. M. Lau, Yunhe Pan · 2003
We introduce a novel intelligent system which can generate new Chinese calligraphic artwork that meets certain aesthetic requirements automatically. In the machine learning phase, parametric representations of the existent calligraphic artwork are derived from input images of calligraphy. Using a six-layer hierarchical representation, the acquired knowledge is organized as a small structural stroke database, which is then exploited by a constraint-based analogous reasoning component to create artwork in new styles. The simulated analogous reasoning can generate new "e-calligraphy", and constraint satisfaction is used to reject the unacceptable results. The combination of knowledge from various input sources creates a huge space for the intelligent system to explore and produce new styles of calligraphy. (http://www.csis.hku.hk/#songhua/ca/ provides supplementary materials on this paper.) Category: H.4 Information Systems Applications: Miscellaneous I.2.6 Artificial Intelligence: Learning [Analogies, Knowledge acquisition] I.3.5 Computer Graphics: Computational Geometry and Object Modeling [Ge- ometric algorithms and systems, Hierarchy and geometric transformations] I.4.9 Image Processing and Computer Vision: Applications J.5 Computer Applications: Art and Humanities [Arts, fine and performing, Fine art ] Keywords: analogous reasoning, simulated analogous reasoning process, character skeletonization, radical extraction, character segmentation, constructive element, topological constructor, hierarchical representation of calligraphic artwork, constraint satisfaction, degree of interference, non-photorealistic rendering 1