Effects of different task factors on speed and preferences in Chinese handwriting

This study was conducted to determine the speed of Chinese handwriting and explore the effects of the task factors, tool type, paper texture, writing plane angle, and line spacing on writing speed and subjective preferences. The results showed that the average duration of writing a 9-stroke character was 1487 ms. Paper texture and line spacing had a significant effect on production speed. Uncoated paper and 3 mm-line spacing enhanced writing speed. Subjects had clear preferences for writing with a pen, on uncoated paper, in a horizontal plane, and with relatively wide line spacing (5 mm/7 mm/lineless). There was a conflict between writing speed and personal preference on the line spacing factor. Although narrow line spacing (3 mm) increased writing speed, it was not preferred by the subjects over wider spacing on the evaluation attributes of comfort, ease, fatigue, and overall preference. To take a balance between writing speed and personal preference, a line spacing of at least 5 mm is recommended.     

面向中文矢量笔迹中单字详细分类的特征和方法比较*

在识别矢量笔迹文本时,不同类型单字需要采用不同识别器,确定详细类别是单字识别的前提。对实际中文矢量笔迹文本中单字进行汉字、标点、数字、字母和单词的详细分类,提出了自身和相对（包括近邻和同行）特征,选用决策树、逻辑模型树、贝叶斯网络和支持向量机四种分类器。针对大量实际数据,测试和比较了多种特征和分类器的性能。实验表明,近邻单字的组合特征具有较好的分类能力,支持向量机对各种单字均有较好分类性能。     

Effects of display method,text display rate and observation angle on comprehension performance and subjective preferences for reading Chinese on an LED display

This study examined the effects of display method, text display rate, and observation angle on comprehension performance and subjective preferences for Chinese characters presented on an LED display. The factors and levels studied were as follows: four text display methods (rapid serial visual presentation ‘RSVP’, leading, paged view scrolling, and continuous scrolling), three text display rates (160 characters per min ‘cpm’, 240 cpm, and 320 cpm), and seven observation angles (−75°, −60°, −30°, 0°, 30°, 60°, and 75°). The results indicated that a display rate of 160 cpm was in general superior to 240 and 320 cpm for comprehension scores and subjective evaluations. The effects of display method and observation angle were found to be non significant. However, there was a significant interaction between display method and display rate. The results of this study were used to make ergonomics recommendations applicable to LED displays for determining optimum dynamic text display methods for Chinese characters.     

一种连续手写中文的演化分割方法

在连续手写中文中,有偏旁部首离得较远的单字,单字之间可能会存在粘连、重叠。针对这种情况给出了一种基于识别得分提取单字的演化方法。对行笔划序列进行二进制编码,采用改进的遗传算法实现演化过程。染色体中连续0或1对应的笔划组成候选单字。用汉王手写单字识别器获取它们的识别得分,以单字个数较少和总的识别得分较大为优化目标。遗传算法中的变异概率和交叉概率自适应生成。测试结果表明该方法对连续手写中文具有较好的分割效果。     

The state of the art in Japanese online handwriting recognition compared to techniques in western handwriting recognition

This paper compares the current state of the art in online Japanese character recognition with techniques in western handwriting recognition. It discusses important developments in preprocessing, classification, and postprocessing for Japanese character recognition in recent years and relates them to the developments in western handwriting recognition. Comparing eastern and western handwriting recognition techniques allows learning from very different approaches and understanding the underlying common foundations of handwriting recognition. This is very important when it comes to developing compact modules for integrated systems supporting many writing systems capable of recognizing multilanguage documents.Received: January 12, 2002, Accepted: March 6, 2003, Published online: 4 July 2003     

Task factor usability ratings for different age groups writing Chinese

This study evaluated how different task factors affect performance and user subjective preferences for three different age groups of Chinese subjects (6–11, 20–23, 65–70 years) when hand writing Chinese characters. The subjects copied Chinese character sentences with different settings for the task factors of writing plane angle (horizontal 0°, slanted 15°), writing direction (horizontal, vertical), and line spacing (5 mm, 7 mm and no lines). Writing speed was measured and subjective preferences (effectiveness and satisfaction) were assessed for each of the task factor settings. The result showed that there was a conflict between writing speed and personal preference for the line spacing factor; 5 mm line spacing increased writing speed but it was the least preferred. It was also found that: vertical and horizontal writing directions and a slanted work surface suited school-aged children; a horizontal work surface and horizontal writing direction suited university students; and a horizontal writing direction with either a horizontal or slanted work surface suited the older adults.     

Off-line recognition of realistic Chinese handwriting using segmentation-free strategy

Great challenges are faced in the off-line recognition of realistic Chinese handwriting. This paper presents a segmentation-free strategy based on Hidden Markov Model (HMM) to handle this problem, where character segmentation stage is avoided prior to recognition. Handwritten textlines are first converted to observation sequence by sliding windows. Then embedded Baum-Welch algorithm is adopted to train character HMMs. Finally, best character string maximizing the a posteriori is located through Viterbi algorithm. Experiments are conducted on the HIT-MW database written by more than 780 writers. The results show the feasibility of such systems and reveal apparent complementary capacities between the segmentation-free systems and the segmentation-based ones.     

Effects of bending curvature and text/background color-combinations of e-paper on subjects’ visual performance and subjective preferences under various ambient illuminance conditions

The study used the simulated e-paper to investigate how the bending radius of curvature (−10 cm, plane, and 10 cm) and 12 text/background color-combinations of e-paper affect subjects’ visual performance and subjective preference under various ambient illuminance conditions (200 and 500 lx). Analysis results indicated that the bending curvature and ambient illuminance did not significantly affect subjects’ visual performance. However, subjects visual performance differed significantly for different text/background color combinations of the simulated e-paper. When the background color of the simulated e-paper was set to yellow-like condition and the luminance of the text was low (2.2 and 4.6 cd/m²), subjects’ visual performance was best. Regarding the subjective preferences of subjects, the results of this research also demonstrated that the bending curvature, text/background color combinations and ambient illuminance all significantly affected the subjective preferences of subjects. Subjects exhibited the best preference under the following settings: bending curvature of the simulated e-paper set to plane; background color of the simulated e-paper set to yellow-like condition and low text luminance (2.2 or 4.6 cd/m²); high ambient illuminance (500 lx).     

Relief算法在笔迹识别中的应用

Relief及其扩展算法是基于最大化假设间隔的特征选择算法,能够快速进行高维度的特征选择。该文围绕汉字笔迹识别,探讨了多类别、样本数量偏差情况对算法过程的影响。文中提出了一种有效应对数量偏差的算法过程,并成功运用于约简高维的笔迹特征。实验表明,改进后的算法不仅节约了处理时间,也进一步改进了特征选择的有效性。     

Effects of display factors on Chinese proofreading performance and preferences

This experiment investigated the influence of four display factors, viz. typeface (Ming Liu and Jheng Hei), font size (10-point and 14-point), text direction (horizontal and vertical) and copy placement (left-right and top-bottom) on Chinese proofreading performance and subjective preferences. Proofreading performance was measured in terms of time and accuracy, and preferences were examined in terms of comfort, ease and fatigue. It was found that the horizontal text direction resulted in faster proofreading than the vertical one, but the other three factors were non significant. The faster proofreading using the horizontal text direction was valid for both the left-right and the top-bottom arrangements. There was an interaction between typeface and font size such that, for the smaller character size (10-point), the Ming Liu style produced a faster performance than the Jheng Hei style. However, for the larger character size (14-point), the Jheng Hei style produced a faster performance than the Ming Liu style. Regarding proofreading accuracy, the number of non-detected missing words and related false alarm in left-right copy placement setting was significantly larger than that in top-down setting. Greater accuracy was obtained in proofreading at the cost of a speed-accuracy trade-off – the higher the accuracy in the proofreading task, the longer the proofreading time. Font size and text direction had significant effects on proofreading preferences, but typeface and copy placement did not.

Practitioner Summary: This study examined four display factors on Chinese proofreading performance and subjective preferences. The findings of this experiment provide information and recommendations that should prove useful for the design of proofreading interfaces to improve proofreading time and accuracy, and to satisfy proofreaders' preference.     

汉字手写笔迹鉴别预处理算法的研究

研究了笔迹鉴别中的各种预处理算法,对传统的方法进行了改进.与传统的预处理方法相比,增加了笔迹图像背景去除、标点去除、汉字过分合并等功能,省去了去除行间和字间的空档的步骤,实现了汉字的任意拼接.以Matlab7.0为开发平台进行了大量的实验,实验结果表明,提出的算法具有处理效果好、可行性强、速度快等优点.最后用20个人120幅样本作对比实验,新算法可以提高笔迹鉴别率5%左右.     

基于多重规则和路径评价的在线中英文手写识别方法

手写文本识别方法主要应用于文本输入技术,对人机交互领域的发展起关键作用。针对多数在线输入法无法识别中英文混合手写识别的问题,提出一种在线中英文混合手写文本识别方法。通过对文本笔画进行基于水平相对位置、垂直重叠率、面积重叠率规则的整合以及连笔切分,得到一系列字符片段,同时利用笔画个数、宽高比、中心偏离、平滑度等几何特征和识别置信度,对字符片段进行中英文分类。在此基础上,根据分类结果并结合自然语言模型的路径评价及动态规划搜索算法,分别对候选的中、英文字符片段进行合并处理,得到待识别的中、英文字符序列,并将其分别送入卷积神经网络的中、英文识别模型中,得到手写文本识别结果。实验结果表明,在线手写中英文混合文本识别正确率达93.67%,不仅能切分在线手写中文文本行,而且对包含字符连笔的在线手写中英文文本行也有较好的切分效果。     

基于多维力传感器的手写信息采集系统设计

针对传统手写信息采集系统存在的信息获取不全面的弊端,设计了一种基于多维力传感器的手写信息采集系统,给出了系统的总体框架.系统以多维力传感器为核心,不仅实现了对手写过程静态轨迹信息的获取,同时实现了对手写多维力信息的获取.整个系统由用户接口模块、数据采集模块和数据处理模块组成,分析了各模块的设计思想和工作原理,并基于WinCE系统开发了一种手写信息采集系统.实验证明：该系统工作稳定,性能优良,实现了对手写过程中力和位置信息的全面获取.     

计算机在中文速记领域中的应用

介绍一种实用于电脑速记的汉字输入法。实践表明,该输入法每分钟可输入200字左右,基本适应速记的要求。     

基于多方向特征融合的维吾尔文笔迹鉴别技术

在笔迹图像中格线和噪音的去除、细化等预处理基础上,结合维吾尔文笔迹结构和书写风格,提出了一种基于四维笔划方向特征的笔迹鉴别技术。为了进一步提高其鉴别率,还将方向特征与较成熟的基于倾斜度的另一种方向特征进行了融合,取得了较好的实验结果。具体实施过程中,还对比分析了不同的特征距离度量方法对鉴别率的影响,确定加权欧式距离为最佳度量方法。     

Retrieval of online handwriting by synthesis and matching

Search and retrieval is gaining importance in the ink domain due to the increase in the availability of online handwritten data. However, the problem is challenging due to variations in handwriting between various writers, digitizers and writing conditions. In this paper, we propose a retrieval mechanism for online handwriting, which can handle different writing styles, specifically for Indian languages. The proposed approach provides a keyboard-based search interface that enables to search handwritten data from any platform, in addition to pen-based and example-based queries. One of the major advantages of this framework is that information retrieval techniques such as ranking relevance, detecting stopwords and controlling word forms can be extended to work with search and retrieval in the ink domain. The framework also allows cross-lingual document retrieval across Indian languages.     

Structural analysis of Arabic handwriting: segmentation and recognition

In this paper, a structural method of recognising Arabic handwritten characters is proposed. The major problem in cursive text recognition is the segmentation into characters or into representative strokes. When we segment the cursive portions of words, we take into account the contextual properties of the Arabic grammar and the junction segments connecting the characters to each other along the writing line. The problem of overlapping characters is resolved with a contour-following algorithm associated with the labelling of the detected contours. In the recognition phase, the characters are gathered into ten families of candidate characters with similar shapes. Then a heterarchical analysis follows that checks the pattern via goal-directed feedback control.     

计算机辅助汉字书写教学技术研究综述

传统的汉字书写教学方法具有一定的局限性,为此人们开始关注计算机辅助的汉字书写教学技术。它主要研究汉字书写规范的智能化、自动化评判方法以及可视化的反馈形式。对近20年来计算机辅助汉字书写教学技术的发展情况进行了综述;详细介绍了数字化展示、书写评判、水平评测等几个研究分支的特点、关键问题以及主要成果;结合相关技术的发展和需求的变化,提出了汉字书写数字化教学技术在未来的发展方向。     

基于混沌序列的SVM参数选择及其在笔迹鉴别中的应用

基于RBF核的支持向量机(SVM)模型选择取决于两个参数，即惩罚因子和核参数，为了寻找SVM参数的最优组合，利于笔迹鉴别图像的自动识别，提出了基于混沌序列的参数搜索算法以实现SVM模型参数的自动选择。从与网格法和双线性法进行的比较实验可以看出，基于混沌序列的SVM参数选取更简单，更易于实现，并使SVM具有更好的推广能力。在10人笔迹灰度图像库上分类识别实验结果表明，该方法不但可以提高分类识别率，而且显著减少了训练SVM的个数。