The authentication and classification of Visual arts used to be depended on the judgment of the artist himself according to experience and knowledge of the artwork and its artist. Recently, the development of computer and image processing technology has made the processing of digital visual artworks possible. More and more museums and libraries have their collections to be digitalized, which make the study of problems haunted the art historians based on these digital images available. In this paper, the research of understanding of visual arts based on computer and low-level information of paintings, which can be called scientific understanding of visual arts, has been brought out. Some features, including multi-scale amplitude, distribution of coefficients of Curvelets and non-stationary of artworks, are extracted to evaluate the style of different artist and some other respects of the artwork. The relations between the style of visual arts and these features are also stated. It is apparent that each feature reflects different characteristics of the painting technique.
