毛笔书写中的笔墨提取与骨架生成  

Ink extraction and skeleton generation in brush writing

作　　者：施霖[1] 张家玮 SHI Lin;ZHANG Jiawei(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650031,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650031

出　　处：《现代电子技术》2023年第23期144-148,共5页Modern Electronics Technique

摘　　要：在数字书法研究中,获取毛笔书写过程中毛笔和墨迹的变化对于获得完整的书写信息至关重要。然而,在毛笔书写过程中,由于墨迹与笔头蘸墨颜色相近且难以有效分离,同时受到笔头对新生成的墨迹覆盖影响,导致实时生成的书法图像中无法准确提取笔墨变化。为了应对这些挑战,文中构建了一个书法运笔处理平台,采用同步采集、畸变矫正和成像对齐,以确保上下相机的成像对齐,并还原真实墨迹轮廓。通过分区分割技术从下方成像中获取完整的墨迹轮廓;采用帧差法从墨迹轮廓中提取墨迹增量,并根据墨迹增量确定墨迹位置变化,从而生成墨迹骨架;根据差分上下成像的方法成功分离出上方成像中的笔头与笔杆区域。实验结果表明,提出的一系列处理方法能够实时提取毛笔书写过程中的墨迹变化与毛笔变化,并生成墨迹骨架,从而为数字书法生成与书法自动评估提供基础研究数据。In the study of digital calligraphy,the variations in brush strokes and ink play a crucial role in capturing complete information in the process of brush writing.However,during the process of brush writing,the similarity in color between the ink and the ink⁃dipped brush tip,along with the overlapping of newly⁃generated ink by the brush tip,hinders the extraction of complete ink variations in real⁃time calligraphy images.To address these challenges,this research establishes a calligraphy stroke processing platform that employs synchronized capture,distortion correction and image alignment to ensure imaging alignment between the top and bottom cameras and restore the actual ink contours.Complete ink contours are obtained from the bottom imaging by partitioning and segmentation techniques.Ink increments are extracted from the ink contours by frame difference method,and ink position changes are determined based on the ink increments to generate ink skeletons.The brush tip and shaft regions in the top imaging are successfully separated according to differential imaging between the top and bottom views.Experimental results demonstrate that the proposed series of processing methods can extract ink contours and brush skeletons in real⁃time during the process of brush writing,which provides fundamental research data for digital calligraphy generation and automated calligraphy assessment.

关 键 词：书法图像 笔墨提取 骨架生成 墨迹增量 墨迹骨架 图像处理 

分 类 号：TN911.73-34[电子电信—通信与信息系统] TP391.1[电子电信—信息与通信工程]