Painting And Calligraphy Assurance Based On Image Feature Matching

The meaning of painting and calligraphy assurance is identification and authentication of the artwork, and to judge whether the painting is the same one recorded or not. Generally speaking, painting and calligraphy assurance relies on the author of the painting or experienced specialists. The rapid development of computer vision technology makes computer-aided assurance possible.The goal of this paper is to study painting and calligraphy assurance by feature-based image matching. With feature-based matching technique, we match the recorded and current images of the artwork, to judge whether these two sets of images come from the same artwork or not. According to the practical application, painting and calligraphy assurance can be divided into two categories. One is the assurance based on platform imaging device. The other is hybrid assurance based on handheld and platform imaging device.Painting and calligraphy assurance based on platform imaging device, means to sample the artwork with platform imaging device when putting on records and identification, and to identify based on these images. It is referred to as platform assurance. In platform assurance, this paper described a method of image matching based on the Speed Up Robust Features algorithm(SURF), and the assurance result depends on matching degree. SURF algorithm has good anti-noise property. It is invariant to image scaling and rotation. Experimental results show that this method can distinguish the original artwork from other artworks. Moreover, it can distinguish different replica of the same artwork. Based on these results and the actual application, we present a cascade painting assurance method. It can distinguish the replica and the original artwork quickly comparing to the previous method.Painting and calligraphy assurance based on handheld and platform imaging device, means to sample the painting with platform when records, and to identify based on the images of poor quality from handheld device. Such hybrid assurance compares the images from different device and gives the preliminary result. Because the images from handheld device are of low quality, any single feature cannot get a satisfactory matching result. So this paper uses an assurance method with multi-feature fusion to solve the quality problem. Experimental results show that the multi-feature fusion method of binary features can solve the matching problem of images of different quality, and the painting assurance result is of high reliability.This paper studies painting assurance with feature-based image matching. Feasible methods are presented for platform and hybrid assurance scenarios, and they show excellent result in experiment.