Skeletons of characters provide vital information to support a variety of tasks, e.g., optical character recognition, image restoration, stroke segmentation and extraction, and style learning and transfer. However, automatically skeletonizing Chinese characters poses a steep computational challenge due to the large volume of Chinese characters and their versatile styles, for which traditional image analysis approaches are error-prone and fragile. Current deep learning based approach requires a heavy amount of manual labeling efforts, which imposes serious limitations on the precision, robustness, scalability and generalizability of an algorithm to solve a specific problem. To tackle the above challenge, this paper introduces a novel three-staged deep generative model developed as an image-to-image translation approach, which significantly reduces the model’s demand for labeled training samples. The new model is built upon an improved G-net, an enhanced X-net, and a newly proposed F-net. As compellingly demonstrated by comprehensive experimental results, the new model is able to iteratively extract skeletons of Chinese characters in versatile styles with a high quality, which noticeably outperforms two state-of-the-art peer deep learning methods and a classical thinning algorithm in terms of F-measure, Hausdorff distance, and average Hausdorff distance.

字符骨架提供重要信息来支持各种任务，例如光学字符识别、图像恢复、笔画分割和提取以及风格学习和迁移。然而，由于汉字数量庞大且样式多样，自动骨架化汉字带来了严峻的计算挑战，传统的图像分析方法容易出错且脆弱。当前基于深度学习的方法需要大量的手动标记工作，这严重限制了解决特定问题的算法的精度、鲁棒性、可扩展性和泛化性。为了应对上述挑战，本文引入了一种新颖的三阶段深度生成模型，作为图像到图像的翻译方法而开发，该模型显着减少了模型对标记训练样本的需求。新模型建立在改进的 G-net、增强的 X-net 和新提出的 F-net 的基础上。综合实验结果令人信服地证明，新模型能够高质量地迭代提取多种风格的汉字骨架，在性能方面明显优于两种最先进的同行深度学习方法和经典的细化算法。F测量、豪斯多夫距离和平均豪斯多夫距离。