Chinese calligraphic artwork usually contains a few or even a single character. In order to perform automatic brush writing style classification on these kinds of Chinese calligraphic images, existing approaches need to be modified because they assume that many characters of the same style exist in the input image. A novel approach is proposed to address the brush writing style classification problem for single-character Chinese calligraphic images by combining the texture analysis and the structural information through a set of parameterised ellipses.