A new artistic information extraction method with multi channels and guided filters for calligraphy works

摘要

The artistic beauty of Chinese calligraphy is constituted by two elements: form and spirit. To learn and study calligraphy works, both of form and spirit should be extracted correctly. However, most currently used calligraphy image extraction methods can only obtain form information. To address this problem, an extraction method, based on multi-channel and guided filters, is proposed in this study. The proposed method consists of three major operations: color space transformation, tablet and writing discrimination, and information extraction using guided filter. To simulate the human visual perception of calligraphy work, the color space of a calligraphy image is converted from RGB to CIELAB firstly. Then the calligraphy image is distinguished as either a tablet or a writing based on channel b. Finally, information extraction using guided filter is performed. For a tablet, a two-stage guided filtering strategy based on L channel is employed to reduce noise and obtain form information. For a writing, a guided filter based on channels L and a is used to extract both form and spirit information. To demonstrate the accuracy and efficiency of the proposed method, comparison experiments are implemented on both types of images. Experimental results reveal the advantages of the proposed method.