Content-Based Identifying and Classifying Traditional Chinese Painting Images

As traditional Chinese painting (TCP) occupies an important place in the life of modern Chinese, there are a lot of TCP images digitalized and exhibited on the Internet. However, effective identification and classification in them are an imperative problem need to be addressed. The paper proposes a content-based identification and classification scheme that represents the visual content of TCP images by chromatic and textural feature set. Four kinds of classifier implemented in the scheme learn the characteristics of fundamental TCP style, art movements and painters. The experimental results show that the scheme is capable of identifying the TCP image and classifying them based on painters as well as art movements with an accuracy of greater than 85%.