基于图像的二维剪纸自动生成方法

中国剪纸的设计极具挑战性, 要求画面简洁、直观, 还需要表达特定的文化内涵, 且整张剪纸须整体连通。提出了一种基于图像的二维剪纸自动生成方法, 能够将任意数码照片自动转化为剪纸图形。首先，利用图像分割方法建立区域连接图; 接着, 基于该连接图对颜色、边界对比度和区域连通性进行数学建模, 并获得优化目标函数; 最后, 通过模拟退火算法求解目标方程, 自动生成保持图像内容的剪纸图形。还开发了连通性后处理和区域指定等用户交互工具, 允许用户在自动生成的剪纸图形中方便地加入个人设计。实验表明, 所生成的剪纸图形画面简洁、整体连通。 本方法在降低剪纸设计难度的同时还可满足个性化的设计需求, 有助于传播和传承我国的民间剪纸艺术。

Image-based automatic generation of 2D paper-cuts

The paper-cut design is very challenging. It should convey rich cultural meanings with a few of simple shapes, and the remains after cut must be connected as an integral piece of work. In this work, we introduce an image-based 2D paper-cut generation method that converts an arbitrary image into a paper-cut pattern automatically. An adjacent graph is first constructed using a segmentation of the input image, and then a paper-cutting mathematical model that consists of color, boundary contrast and connectivity constraints is proposed, the final paper-cut pattern is computed by solving this model as an optimization problem. User-friendly interaction tools like connectivity post-processing and region assignment are provided, which allow the users to easily add their personal designs into the automatically generated paper-cuts. Experiments demonstrate the proposed method can generate feature-preserved and geometry-connected paper-cuts, it reduces the design difficulty while satisfying users’ personalized demand, which contributes to the transmission and inheritance of our folk paper-cut art.