Learning A Stroke‐Based Representation for Fonts

Designing fonts and typefaces is a difficult process for both beginner and expert typographers. Existing workflows require the designer to create every glyph, while adhering to many loosely defined design suggestions to achieve an aesthetically appealing and coherent character set. This process can be significantly simplified by exploiting the similar structure character glyphs present across different fonts and the shared stylistic elements within the same font. To capture these correlations, we propose learning a stroke‐based font representation from a collection of existing typefaces. To enable this, we develop a stroke‐based geometric model for glyphs, a fitting procedure to reparametrize arbitrary fonts to our representation. We demonstrate the effectiveness of our model through a manifold learning technique that estimates a low‐dimensional font space. Our representation captures a wide range of everyday fonts with topological variations and naturally handles discrete and continuous variations, such as presence and absence of stylistic elements as well as slants and weights. We show that our learned representation can be used for iteratively improving fit quality, as well as exploratory style applications such as completing a font from a subset of observed glyphs, interpolating or adding and removing stylistic elements in existing fonts.     

基于形态学的新的汉字字形自动生成方法

电子印刷,桌面出版,艺术,广告等领域对不同风格汉字的需求,迫切需求一种自动的汉字字形生成方法。传统方法只适用于两种字形相关不大的字体进行合成,并且需人干预,本文通过对字体的凸剖分,并建立两种不同字体的子凸集映射,提出了一种全新的基于形态变换的汉字形自动生成方法,     

汉字字形的凸剖分变形及合成

文中提出了一种全新的基于凸多边形变形的汉字字形自动生成方法. 通过对字体的凸剖分,把字体分解成若干个子凸多边形,并经过全局优化迭代建立两种不同字体的子凸多边形间的匹配关系,计算两匹配子凸多边形的形态和,再进行合并,则得到合成后的字体.理论上证明了此方法的正确性,讨论了不同剖分对生成字形的影响,可解决不同构字体间的合成问题,通过不同的结构元的形态变换,实现不同字体的衍生.实验证明此方法生成的汉字字形多,质量好,自动化程度高,并可用于三维字体生成.     

Text legibility and the letter superiority effect

Effects of font design and electronic display parameters upon text legibility were determined using a threshold size method. Participants' visual acuity (inverse of the minimum detection size, representing the threshold legibility for each condition) was measured using upper- and lowercase letters and lowercase words in combinations of 6 fonts, 3 font-smoothing modes, 4 font sizes, 10 pixel heights, and 4 stroke widths. Individual lowercase letters were 10% to 20% more legible than lowercase words (i.e., lowercase words must be 10%-20% larger to have the same threshold legibility). This letter superiority effect suggests that individual letters play a large role and word shape plays a smaller role, if any, in word identification at threshold. Pixel height, font, stroke width, and font smoothing had significant main effects on threshold legibility. Optimal legibility was attained at 9 pixels (10 points). Verdana and Arial were the most legible fonts; Times New Roman and Franklin were least legible. Subpixel rendering (ClearType) improved threshold legibility for some fonts and, in combination with Verdana, was the most legible condition. Increased stroke width (bold) improved threshold legibility but only at the thinnest width tested. Potential applications of this research include optimization of font design for legibility and readability.     

基于汉字字体结构认知计算的多意象预测模型

为了揭示汉字字体与受众的情感意象之间的内在关系，从认知计算的角度出发， 探索构建一种“设计特征-结构指标-意象”的灰箱关联模型，以其预测汉字字体的多个意象。首 先依据认知计算的原理将字体结构规则抽象为知识，运用产生式规则将字体结构知识进行定量 描述，提出字重、重心、字面、字怀 4 个字体结构指标的认知计算公式，将无序的形态信息转 化为结构化的有序信息。然后基于汉字字体意象认知系统的非线性耦合的特点，发展出一种运 用多输出最小二乘支持向量回归机(MLS-SVR)进行汉字字体多意象预测的方法。将该方法对汉 字字体的 3 个意象进行预测，实验结果表明其具有良好的预测效果和精度。该模型可作为字体 智能设计系统的适应度函数，为发展字体智能设计提供有益的参考。     

基于CapsNet的汉字字形表征模型

提出基于胶囊神经网络(CapsNet)的汉字字形表征模型,通过表征汉字字形中的部件实现汉字字形的表征.首先,对任一汉字字形生成所有部件类别的表征向量.然后,根据部件存在概率,利用基于欧氏距离的离群点检测,选取相应的部件表征向量.最后,由选出的部件表征向量组成该汉字的字形表征.实验表明,文中模型在仅经过部件字形训练的情况下,即可有效识别汉字部件,同时自动生成汉字字形的有效表征.     

Substituting outline fonts for bitmap fonts in archived PDF files

As collections of archived digital documents continue to grow the maintenance of an archive, and the quality of reproduction from the archived format, become important long‐term considerations. In particular, Adobe's portable document format (PDF) is now an important ‘final form’ standard for archiving and distributing electronic versions of technical documents. It is important that all embedded images in the PDF, and any fonts used for text rendering, should at the very minimum be easily readable on screen. Unfortunately, because PDF is based on PostScript technology, it allows the embedding of bitmap fonts in Adobe Type 3 format as well as higher‐quality outline fonts in TrueType or Adobe Type 1 formats. Bitmap fonts do not generally perform well when they are scaled and rendered on low‐resolution devices such as workstation screens. The work described here investigates how a plug‐in to Adobe Acrobat enables bitmap fonts to be substituted by corresponding outline fonts using a checksum matching technique against a canonical set of bitmap fonts, as originally distributed. The target documents for our initial investigations are those PDF files produced by LATEX systems when set up in a default (bitmap font) configuration. For all bitmap fonts where recognition exceeds a certain confidence threshold replacement fonts in Adobe Type 1 (outline) format can be substituted with consequent improvements in file size, screen display quality and rendering speed. The accuracy of font recognition is discussed together with the prospects of extending these methods to bitmap‐font PDF files from sources other than LATEX. Copyright © 2003 John Wiley & Sons, Ltd.     

数字化藏文古籍中多样性字体的实现方法研究

After the computer became a tool for data sharing and information exchange, the unified computer font has made the text lose the diversity and discreteness of handwriting. Text is the crucial factor for the spread of culture and civilization. Many electronic books have lost the characteristic fonts with cultural background and historical significance in the original ancient books after the digitalization. One example is the sculpted typeface with diversity and discreteness that can be called a Tibetan culture. In order to solve this problem, a research method of digitizing engraving fonts in ancient Tibetan books is proposed. Firstly, the projection method and the connected domain method are used to segment the ancient book image. Secondly, the GIST feature algorithm is used to realize the image text recognition. Thirdly, the SIFT feature algorithm is used to implement the image font style classification, and diffe rent styles of carved fonts in the ancient books are obtained. A font diversity expression algorithm is proposed to realize the diversity and discreteness of carved fonts in ancient books. The purpose of the research is to achieve the inheritance and protection of engraving fonts, which has important cultural research and inheritance significance.     

一种女书手写字符规范字形自动生成方法

中国女书是具有鲜明民族特色的文字,目前国内还没有公认的女书规范字库。针对手写体文字规范化字体生成过程多采用人工修正方式、效率低下的现状,该文设计了一种女书手写字符规范字自动生成方法。基于手写文字样本,提取其单像素骨架,并结合字符轮廓信息进行骨架畸变点校正;然后提取骨架特征点和笔段,根据笔段连通性和交角情况建立笔段关联矩阵;基于笔段关联矩阵由笔段恢复笔画,获取笔画路径关键点序列;最后基于三次Bezier曲线重绘字符笔画并均匀加粗,形成笔画粗细一致、平滑无毛刺、无畸变的规范字体。实验结果表明,该方法自动便捷,效果良好,效率优于人工方式,经改进后可以推广到其他手写字符的规范化过程。     

一种提升小曲线轮廓字体显示品质的算法

提出了一种用于手持显示器设备的提升显示小曲线轮廓字体的还原质量算法。本算法由三个步骤组成，首先根据字体曲线的曲率动态离散曲线，利用小字体在低像素的特点，根据斜率和分辨率的大小进行去冗余操作，最后对字体边缘进行微调。实验结果表明，本算法提高了小曲线轮廓字体的字形显示质量，降低了对设备的内存需求，提高了字体的显示速度。     

维哈柯文字库标准符合性检测研究

在调查和分析维哈柯文字库存在问题的基础上,依据国家制定的维哈柯文字符集标准与字形标准,明确了维哈柯文字库标准符合性检测的含义与内容,结合对TrueType字形技术,TrueType字库文件基本构成的详细研究,提出了完整的维哈柯文字库标准符合性检测的方案与算法,并实现了维哈柯文字库标准符合性检测工具的开发.实验结果表明检测方案完整、可行,能较好地解决维哈柯文字库标准符合性检测问题,对其它文字的字库标准符合性检测也具有一定的借鉴意义.     

Analysis of the representative shape classification features of Hangul font services

There are various design guidelines for choosing Roman font that can strengthen the effectiveness and significance of visual delivery by using changes in font shape. However, it is not easy to apply Roman font guide directly to Hangul. The structural characteristics of Hangul fonts may be the cause. It means that Hangul fonts are composed of vowels and consonants with a structure that consists of an initial, middle, and final sound; there are shape properties that differ from existing Roman font design properties. Therefore, the representative shape features must also be defined differently. Moreover, although there are Korea standards related to shape features, it is impossible to systematize them using a classification standard with a visual or cognitive basis. This study identified 10 representative shape features based on a statistical analysis of 100 Hangul fonts and 75 shape features presented by previous studies. The validity of utilizing Hangul fonts with respect to the newly presented representative shape features was verified in this investigation. The shape features presented in this study will be proposed as a shape feature standard for Hangul fonts and may be used in the recommendation system.     

VxWorks5.5 平台下矢量字体显示的实现

VxWorks5.5采用点阵字库实现字体显示,这种字库设计简洁,应用广泛,但一个字库只能对应一种字体的一种大小,在不确定使用何种字体的情况下,这种传统的字体显示方式便不能够满足需求。通过使用TrueType字库和FreeType字体引擎相结合的方式,能实现多种字体、任意大小的显示功能。主要介绍了TrueType、FreeType技术的基本原理,以及在VxWorks5.5下如何将WindML、FreeType和TrueType三者相结合实现矢量字体显示的方法。     

一种新的矢量中文字库自动压缩方法

针对中文矢量字库体积较大,在嵌入式设备上使用不便的问题,提出了一种新的矢量中文字库自动压缩方法.基于部件拼接和复用的思想,首先使用一种传统图形学方法将字库中的字形拆分成不同部件,之后计算每个字形的部件复用关系,最后使用模拟退火算法迭代优化拼接字形,生成压缩字库.实验结果表明,该方法能够在维持原始字库风格和字形不变的条件...     

KAFD Arabic font database

Font recognition is useful for improving optical text recognition systems’ accuracy and time, and to restore the documents’ original formats. This paper addresses a need for Arabic font recognition research by introducing an Arabic font recognition database consisting of 40 fonts, 10 sizes (ranging from 8 to 24 points) and 4 styles (viz. normal, bold, italic, and bold–italic). The database is split into three sets (viz. training, validation, and testing). The database is freely available to researchers.¹ Moreover, we introduce a baseline font recognition system for benchmarking purposes, and report identification rates on our KAFD database and the Arabic Printed Text Image (APTI) database with 20 and 10 fonts, respectively. The best recognition rates are achieved using log-Gabor filters.     

Extraction of Typographic Elements from Outline Representations of Fonts

Digital typefaces for computer graphics and multimedia applications should be capable of supporting operations such as font variations, transformations. deformations and blending. A powerful implementation of such operations must rely on the inherent typographic attributes of the typeface. However, even today's most advanced typeface representations support only geometric outline representations and basic font variations. In this paper we discuss high-level typeface representations which we term Parametric Typographic Representations (PTRs). We present an algorithm for automatically extracting typographic elements of typefaces from their outline representation, which, is an essential initial step in converting typefaces from outline representations to PTRs. The extracted typographic elements include serifs, bars. sterns, slants, bows, arcs, curve stems and curve bars. Most notable is the treatment of serifs, which are represented by finite-automata. The algorithm only needs to learn a serif type once, and is then capable of automatically recognizing it in different typefaces. We show an application of a PTR for automatic high-quality hinting of fonts, which is one of the most important stages in, digital font production. Our system was used to generate hints for dozens of thousands of Kanji, Roman and Hebrew characters.     

Measuring Software Screen Complexity: Relating Eye Tracking,Emotional Valence,and Subjective Ratings

Enterprise software pages, routinely used to conduct a variety of business-relevant tasks, must be clear and nonconfusing to experienced end users. A study was conducted to consider the impact of several page design factors (background gradient, font, and font size) on perceived ratings of page clarity, completion time, emotional valence (EV) from video, and several eye-tracking parameters. Twenty professional managers each completed 25 tasks on enterprise web pages designed with specific combinations of these factors. Highly rated pages had Tahoma and Larger fonts, compared to Calibri and Smaller fonts. The Gradient background did not influence ratings but did increase the search area and completion time. Although EV was not a sensitive measure across tasks, it was influenced by font differences in the first few seconds of page presentation. Overall, the use of background gradient was not supported, but both Tahoma and Larger fonts were supported for these enterprise pages.     

An efficient raster font compression for embedded systems

This paper presents a new lossless raster font compression method that uses vertex chain code to define character’s outline. Obtained chain codes are compressed by Huffman coding algorithm. The results show that the new method requires least memory space to store the raster fonts among the known methods. Moreover, the font size has almost no impact on the coder efficiency. Due to the low complexity of the decoder that occupies only 2.7 kB of memory space, this method is ideal for use in embedded systems.