基于t-SNE的爨宝子碑文字体流形分析  

Font Manifold Analysis of Cuanbaozi Inscription Based on t-SNE

作　　者：王静博 王存睿 战国栋 WANG Jingbo;WANG Cunrui;ZHAN Guodong(School of Computer Science and Engineering,Dalian Minzu University,Dalian Liaoning 116605,China;School of Design,Dalian Minzu University,Dalian Liaoning 116605,China;Dalian Chinese Font Design Technology Innovation Center,Dalian Minzu University,Dalian Liaoning 116605,China)

机构地区：[1]大连民族大学计算机科学与工程学院,辽宁大连116605 [2]大连民族大学设计学院,辽宁大连116605 [3]大连民族大学大连市汉字计算机字库设计技术创新中心,辽宁大连116605

出　　处：《大连民族大学学报》2025年第1期47-52,共6页Journal of Dalian Minzu University

基　　金：辽宁省技术攻关项目(2024JH2/102600108);大连市科技创新基金项目(2023JJ12GX026);云南师范大学教育部民族教育信息化重点实验室基金项目(EIN2024B002)。

摘　　要：提出一种基于t-SNE(t-Distributed Stochastic Neighbor Embedding)降维、稀疏学习特征提取与欧氏距离相似度分析的书法字体比较方法。首先,通过t-SNE对高维字体样本数据进行降维,找出潜在的流形结构;然后利用稀疏学习从降维后的数据中提取关键特征,进一步表征三种字体的风格特性;最后基于欧氏距离计算不同字体间的相似度,量化书法风格的异同。实验结果表明:爨宝子、隶书和楷书在流形空间中表现出各自独特的分布特征,同时在部分区域存在显著重叠,验证了三种字体在书法风格上的相似性。This paper proposes a method for comparing calligraphic fonts based on t-SNE(t-Distributed Stochastic Neighbor Embedding)dimensionality reduction,sparse learning feature extraction,and Euclidean distance similarity analysis.First,t-SNE is used to reduce the dimensionality of high-dimensional font sample data,revealing their underlying manifold structures.Next,sparse learning is employed to extract key features from the reduced data,further characterizing the stylistic traits of the three fonts.Finally,Euclidean distance is applied to calculate the similarity between different fonts,quantifying the similarities and differences in calligraphic styles.Experimental results show that the fonts,Cuanbaozi,Lishu and Kaishu exhibit unique distribution characteristics in the manifold space,while significant overlaps are observed in certain regions,confirming their stylistic similarities in calligraphy.

关 键 词：图像降维 小样本 字体比较 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]