Research on quantifying color of HSV in extraction of middle-level semantic objects of traditional Chinese painting images

摘要

Tra dit io n a l Chinese painting is a unique form of art and highly regarded for its theory, expression and techniques throughout the world. The scripts part and the seals part of the traditional Chinese painting images are integral parts of traditional Chinese paintings and have high semantics. The automatic extraction of these two parts becomes a key problem. The seals part and scripts part are mostly in black ink and red color respectively. To extract them, the black or red regions should be first extracted. In the paper, we focus on how to quantify color of HSV to get better extracted results according to the characteristics of traditional Chinese painting images. A color quantifying model is given first. Then the results under different quantifying value are analyzed in details. The extracted results are satisfactory. The work of the paper is very meaning to further extract the scripts part and the seals part of traditional Chinese painting images accurately.