Model-based analysis of Chinese calligraphy images

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

35 Scopus Citations
View graph of relations

Related Research Unit(s)


Original languageEnglish
Pages (from-to)69-85
Journal / PublicationComputer Vision and Image Understanding
Issue number1
Publication statusPublished - Jan 2008


A lot of research and development have been done on producing Chinese fonts with smooth outlines and solid colouring for computer displays and printing. Existing Chinese fonts however are not able to reproduce or convey the aesthetic properties of the characters produced by calligraphers. Ip and Wong proposed a parameterised brush model called the Virtual Brush, which enables efficient representation and generation of Chinese calligraphic writings such that the rendering is scalable in resolution and allows high quality publishing. While other researchers always focus on synthesis, we are working as a pioneer on the reverse problem-calligraphic image analysis. Given a static calligraphic image, it is a labour-intensive task to construct a set of 3-D geometric and writing model parameters to obtain a dynamic representation. It is therefore desirable to develop an automated approach to estimate the Virtual Brush parameters from images of Chinese calligraphy. This paper describes a methodology of a statistical-based approach with image processing techniques for the automatic estimation of the set of Virtual Brush writing parameters, such as the properties of brush hair and variations of ink deposition along a stroke trajectory, directly from an image of calligraphic writing. With our proposed approach, raw digitalised images of Chinese calligraphic writings could be analysed automatically for storage and subsequent synthesis for high quality publishing of Chinese characters in different styles and calligraphic artwork. © 2007 Elsevier Inc. All rights reserved.

Research Area(s)

  • Automatic brush parameter estimation, Chinese calligraphy images, Model-based analysis, Virtual Brush