Recognition of Chinese artists via windowed and entropy balanced fusion in classification of their authored ink and wash paintings (IWPs)》.pdf

Pattern Recognition 47 (2014) 612–622 Contents lists available at ScienceDirect Pattern Recognition journal homepage: /locate/pr Recognition of Chinese artists via windowed and entropy balanced fusion in classification of their authored ink and wash paintings (IWPs) Jiachuan Sheng a, Jianmin Jiang b,c,n a School of Science Technology, Tianjin University of Finance Economics, China b School of Computer Science Technology, Tianjin University, China c Department of Computing, University of Surrey, United Kingdom a r t i c l e i n f o a b s t r a c t Article history: As one of the most important cultural heritages, ink and wash paintings (IWPs) play an important role in Received 1 February 2013 the world of traditional Chinese arts. In comparison with western arts, the Chinese IWPs have the unique Received in revised form feature that the art form is primarily populated with limited number of content elements, such as stones, 16 August 2013 mountains, flowers, and animals etc. and hence most likely different art pieces share similar content, Accepted 19 August 2013 making it difficult to differentiate in terms of content alone. In this paper, we propose to extract Available online 30 August 2013 histogram-based local feature and global feature to characterize different aspects of art styles, and such Keywords: features are applied to drive neural networks to complete the classification of IWPs in term