Chinese painting and calligraphy image recognition technology based on pseudo linear directional diffusion equation

Abstract In order to study the image recognition technology of traditional Chinese painting and calligraphy based on pseudo linear directional diffusion equation. Firstly, in pixel domain, an overall style feature extraction algorithm ink histogram is proposed, then local area with most representative stroke located Sobel edge detection method obtain detail information describing stroke. Then, using processing, computer vision other technologies, combined some quantifiable authenticity identification indexes painting, this paper designs a assist improve reliability identification. The experimental results show that fusion algorithms entropy distance are proposed paper. On premise maximizing artistic style, combines advantages class results, so as realize automatic classification output results.