毛笔书写视频中运笔骨架动态提取方法  

Dynamic extraction method of brush moving skeleton in brush writing video

作　　者：夏曦 申子宜 王佳玉 覃璐 施霖[1] XIA Xi;SHEN Zi-yi;WANG Jia-yu;QIN Lu;SHI Lin(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《陕西理工大学学报（自然科学版）》2022年第4期14-22,共9页Journal of Shaanxi University of Technology:Natural Science Edition

摘　　要：书法字的骨架提取即细化,是书法风格研究的重要先决步骤,针对传统算法提取的骨架易形变和分叉、抗噪声能力差等缺点,提出了一种基于书写过程中墨迹增量的毛笔字骨架动态提取算法。通过搭建的平台采集到毛笔书写视频,对视频进行了畸变矫正和倾斜矫正处理,最后计算了视频单位时间内墨迹增量的中心点,并将其依次相连,实现了对毛笔字形骨架的动态提取。通过对比实验表明:此算法相较于传统算法,能在保证笔画连通性的基础上,尽可能避免骨架的畸变,提取的骨架更能接近“书法骨架”的概念。The skeleton extraction and refinement of calligraphy characters is an important prerequisite step in the study of calligraphy style.Aiming at the shortcomings of traditional algorithms,such as easy deformation and bifurcation and poor anti-noise ability,this paper proposes a dynamic skeleton extraction algorithm based on ink increment in writing process.The center point of ink increment per unit time is calculated through the brush writing video collected by the platform,which is connected in turn to realize the dynamic extraction of brush font skeleton.Finally,the comparative analysis shows that compared with the traditional algorithm,this algorithm can avoid skeleton distortion as much as possible on the basis of ensuring stroke connectivity,and the extracted skeleton is closer to the concept of“calligraphy skeleton”.

关 键 词：毛笔字形 视频处理 骨架提取 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]