The color design is one of the important parts of GUI development. To gain an attractive color scheme, designers often seek inspiration from examples. However, transferring an example’s colors to a target web page is time-consuming and tedious. In this paper, we propose a method named AutoWPR to reuse the example web page’s colors for recoloring a web page. To preserve the semantic relations of web elements, we propose a clustering algorithm to group the related elements into a cluster. In order to make the recoloring result have similar color distributions to the example, we use the Random–Forest regression to learn human’s mappings and propose a top-down matching algorithm to generate a mapping between two web pages’ clusters. Then AutoWPR recolors the element with the matching element’s colors. We designed several experiments to evaluate the correctness of the clustering and matching algorithm. We also conducted some qualitative and quantitative experiments to evaluate the effectiveness of our results in helping recoloring. The results show that our method can generate a human-like recoloring result and help novice developers reuse the reference web page’s colors conveniently.

中文翻译：

---

AutoWPR：一种自动网页重新着色方法

色彩设计是GUI开发的重要组成部分之一。为了获得有吸引力的配色方案，设计师经常从示例中寻求灵感。但是，将示例的颜色传输到目标网页既费时又乏味。在本文中，我们提出了一种名为 AutoWPR 的方法来重用示例网页的颜色来重新着色网页。为了保留网络元素的语义关系，我们提出了一种聚类算法，将相关元素分组到一个簇中。为了使重新着色结果具有与示例相似的颜色分布，我们使用 Random-Forest 回归来学习人类的映射，并提出一种自上而下的匹配算法来生成两个网页集群之间的映射。然后 AutoWPR 使用匹配元素的颜色重新着色元素。我们设计了几个实验来评估聚类和匹配算法的正确性。我们还进行了一些定性和定量实验，以评估我们的结果在帮助重新着色方面的有效性。结果表明，我们的方法可以生成类似人类的重新着色结果，并帮助新手开发人员方便地重用参考网页的颜色。