A Novel Three-Staged Generative Model for Skeletonizing Chinese Characters with Versatile Styles  

作　　者：田业川 徐颂华 Cheickna Sylla Ye-Chuan Tian;Song-Hua Xu;Cheickna Sylla(School of Mathematics and Statistics,Xi’an Jiaotong University,Xi’an 710000,China;Martin Tuchman School of Management,New Jersey Institute of Technology,Newark 07101,U.S.A.)

机构地区：[1]School of Mathematics and Statistics,Xi’an Jiaotong University,Xi’an 710000,China [2]Martin Tuchman School of Management,New Jersey Institute of Technology,Newark 07101,U.S.A.

出　　处：《Journal of Computer Science & Technology》2023年第6期1250-1271,共22页计算机科学技术学报（英文版）

基　　金：supported by the“2030 Major Project-New Generation Artificial Intelligence”funded by the Chinese Ministry of Science and Technology under Grant No.2020AAA0106302;the National Natural Science Foundation of China under Grant No.6187615.

摘　　要：Skeletons of characters provide vital information to support a variety of tasks,e.g.,optical character recogni-tion,image restoration,stroke segmentation and extraction,and style learning and transfer.However,automatically skele-tonizing 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,robust-ness,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 signifi-cantly reduces the model's demand for labeled training samples.The new model is built upon an improved G-net,an en-hanced 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.

关 键 词：skeletonization of characters three-staged skeletonization X-net 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]