Research On Sketch And Chinese Ink Painting Stylization For Image

With the increasing development of computer technology, realistic image rendering technology is tending to be mature. Its aim is to make images look real. However, with the development of the real image simulation techniques, non-realistic image simulation draws the scholars’attention. NPR (Non-Photorealistic Rendering) doesn’t pursue the realism. Its main purpose is to use computer technology to express an object in a concise and subtle way with the aesthetic characteristics. Image stylization processing belongs to NPR. It refers that through computer technology, a common image is processed into a hand-painted image such as oil paintings, watercolors, cartoons, sketch and so on. This article describes image processing algorithm of two typical style, sketch and ink paintings. Sketch stylization algorithms have already been studied by many scholars. But the results are less than ideal. Ink painting as Chinese traditional art form, its simulation is even fewer. Therefore, this article proposed the algorithm of the both style. The effect is promising and the research has certain value.Firstly, we present a new algorithm for automatically generating pencil-sketch like drawings from photos. The existing algorithms were almost in terms of geometry and stroke, or only used classic edge detection method to extract image edge characters. Our proposed algorithm used image-based non-stroke and color dodge blend based method to generate the sketch effect. It can keep not only the image edge information but also the important detail characters through minimum filters of the anti-image and effective layer blend mode. Through minimum filters, the image edge features are kept and enhanced. Through color dodge blend mode, the other parts are faded out. The experiment results show that this algorithm not only reflects the high light, shade, border areas but also keeps the important details of the input image.Then, we propose a method for image-based and ink-diffusion-based Chinese ink painting NPR. Users without painting experience can also convert a normal image to a Chinese ink painting automatically. As we known, ink is an important pigment for Chinese ink painting and the various ink shade effects on the painting are produced by ink mixed with water. In addition, the ink diffusion along the boundaries is a very important aspect of Chinese ink painting. In order to realize the effects described above, we present a Chinese ink painting NPR method based on ink diffusion. We use Mean Shift based image segmentation algorithm to preprocess the input image to get regions with different tones. Then, we detect the segmentation regions’ edges letting the edge points to be the start points for diffusion. At the same time, a new algorithm simulating ink diffusion is proposed to make the segmentation image look like a black-ink painting. Results in this paper demonstrate our method is promising.