首页> 外文会议>Conference on Metrology for Archaeology and Cultural Heritage >Automatic Writer Identification in Medieval Books
【24h】

Automatic Writer Identification in Medieval Books

机译:中世纪书籍自动作家识别

获取原文

摘要

Palaeography aims to study ancient documents, with the identification of the writer hands being one of the most important problems. Over the years, experienced palaeographers have devised many methodological approaches for writer identification. These methodologies are based on traditional palaeographical tools to measure quantities such as letter heights and widths, distances between characters, angles of inclination and number and types of abbreviations. Even if there has been a growing interest in the use of computer science techniques in palaeographic research, there is no general consensus about the effectiveness of such techniques and the main problems in this research field are very far to be solved in the general case. In the context of highly standardized handwriting, the use of some basic features related to the page layout can be very helpful for automatically distinguishing different scribal hands. These features have the advantage of being easily extracted using standard image processing algorithms. In this paper we present a classification tool for helping the palaeographer's work, based on basic layout measures taking into account some general properties related to the organization of the whole page (such as margins, distance between columns, etc.), and some specific properties characterizing the ability of the writer to exploit the available space and to distribute the text in each row. The experimental results, performed on two sets of digital images of two whole Bibles of the XII century, show that using only few pages of these ancient documents for the training phase of the classifier, it is possible to automatically identify the writers on the remaining pages.
机译:古图谱旨在研究古代文件,识别作者手是最重要的问题之一。多年来,经验丰富的掌签已经设计了作者识别的许多方法论方法。这些方法基于传统的掌签工具来测量诸如字母高度和宽度的数量,字符之间的距离,倾斜角度和缩写的类型和类型。即使在古地理研究中使用计算机科学技术的兴趣日益增长的兴趣,对这种技术的有效性没有一般性共识,并且在一般情况下,该研究领域的主要问题远远难以解决。在高度标准化的笔迹的背景下,使用与页面布局相关的一些基本功能对于自动区分不同的血罩手来非常有用。这些特征具有使用标准图像处理算法容易地提取的优点。在本文中,我们提出了一个分类工具,用于帮助古影师的工作,根据基本的布局措施,考虑到整个页面的组织(如利润率,列之间的距离等)以及一些特定的属性表征作者利用可用空间并在每行中分发文本的能力。实验结果,对XII世纪的两个整个圣经的两套数字图像进行了,表明,仅使用这些古代文档的几页进行分类器的训练阶段,可以自动识别剩余页面上的作者。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号