科研之友
微信
新浪微博
Facebook
分享链接
摘要
Linear gradients are commonly applied in non-photographic artwork for shading and other artistic effects. It is sometimes necessary to generate a vector graphics form of raster images comprising such artwork with the expectation to obtain a simple output and plug it into a traditional workflow, to be further edited and arranged. Many such workflows support only linear gradients and our goal is to generate a standard vector form of the image that can fit such workflow. This vectorization process should be automatic with minimal user intervention. We present a simple image vectorization algorithm that detects regions of linear gradient in potentially noisy images and reconstructs the vector definition on the basis of that information. It uses a novel interval gradient optimization scheme to derive large regions of uniform gradient. We also demonstrate the technique on noisy and hand-drawn portraits.
- 出版日期2015-5
