Development of OCR (optical character recognition) system for scientific documents

科学文献OCR（光学字符识别）系统开发

• 批准号: 10558056
• 负责人: SUZUKI Masakazu
• 金额: $ 8万
• 依托单位: KYUSHU UNIVERSITY
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 1998
• 资助国家: 日本
• 起止时间: 1998 至 2001
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-10558056/
• 关键词: OCR; Mathematical symbol recognition; Mathematical formual recognition; Document Analysis; Digital library; レイアウト解析; 文書電子化; 数学記号認識; OCR; ヤグメンテーション; 手書き数式認識; 光学文字認識

In this research, we developed an OCR system adapted to scientific documents, in view of its application to retro-digitization of mathematical journals and automatic Braille transcription of mathematical documents. The target images are those obtained from clearly printed documents by 400-600DPI scanner.Since there is no commercial OCR software which can recognize mathematical symbols, we developed our own OCR engine. It recognizes with about 450 kinds of characters and symbols used in mathematical expressions, and distinguishes well the italic fonts and upright fonts of alphabets.For the recognition of text areas, there are several efficient post-processing methods to improve recognition results using linguistic information, while in mathematical expression areas, some other different methods of post-processing based on the structure of mathematical notations are efficient. Therefore, we developed algorithms to separate text area and mathematical expression areas, for both Japanese and English documents.As for the structure analysis of mathematical expressions, we developed a new method, robust against the recognition errors of characters and similar characters of different sizes. We first construct a network joining characters (symbols) by possible links of relations with cost, Finally, we obtain the result of the recognition of mathematical formulas as the spanning tree of minimum cost of the network, after reevaluating the candidates by using the cost reflecting global structure of the mathematical expressions. The advantage of this method is that local errors of the recognition are recovered automatically by the total cost of the recognition tree.We also developed handwriting interface to edit mathematical expressions to use it as an easy user interface to correct the recognition errors of mathematical expressions.

在这项研究中，我们开发了一个OCR系统，适用于科学文献，鉴于其应用到数学期刊的逆向数字化和自动盲文转录的数学文件。目标图像是由400- 600 DPI扫描仪从清晰打印的文档中获取的图像。由于没有商业OCR软件可以识别数学符号，我们开发了自己的OCR引擎。它识别了大约450种数学表达式中使用的字符和符号，并很好地区分了字母的斜体和直立字体。对于文本区域的识别，有几种有效的后处理方法可以利用语言信息来改善识别结果，而在数学表达式区域，基于数学符号结构的一些其它不同的后处理方法是有效的。因此，我们开发了分离日文和英文文档的文本区域和数学表达式区域的算法，对于数学表达式的结构分析，我们开发了一种新的方法，该方法对不同大小的字符和相似字符的识别错误具有鲁棒性。我们首先用可能的代价关系连接字符（符号）构造一个网络，最后用反映代价的数学表达式的全局结构重新评价候选项，得到数学表达式作为网络最小代价生成树的识别结果.该方法的优点是识别的局部错误可以通过识别树的总代价自动恢复。我们还开发了手写界面来编辑数学表达式，将其作为一个简单的用户界面来纠正数学表达式的识别错误。

项目成果

村上玄生, 鈴木昌和: "Center Bandを用いた数式構造解析の安定化"電子情報通信学会技術研究報告. PRMU2001-270. 203-210 (2002)

Geno Murakami、Masakazu Suzuki：“使用中心频带的数学结构分析的稳定性”IEICE 技术研究报告 203-210 (2002)。

金堀利洋, 鈴木昌和: "可変ブロックパターンによる矩形領域分割を用いた行列の認識"信学技法. PRMU2000-201. 1-6 (2001)

Toshihiro Kanahori、Masakazu Suzuki：“使用可变块模式的矩形区域分割的矩阵识别”PRMU2000-201 (2001)。

Y.Eto., M.Suzuki: "Mathematical Formula Recognition Using Virtual Link Network"Proceedings of the Sixth International Conference on Document Analysis and Recognition, Seattle, IEEE Computer Society Press. 430-437 (2001)

Y.Eto.，M.Suzuki：“使用虚拟链路网络的数学公式识别”第六届国际文档分析与识别会议论文集，西雅图，IEEE 计算机学会出版社。

T.Kanahori, K.Tabata, W.Cong, F.Tamari, M.Suzuki: "On-Line Recognition of Mathematical Expressions Using Automatic Rewriting Method"Advances in Multimodal Interfaces-ICMI2000, Lecture Notes in Computer Science 1948, Springer. 394-401 (2000)

T.Kanahori、K.Tabata、W.Cong、F.Tamari、M.Suzuki：“使用自动重写方法在线识别数学表达式”多模态接口的进展 - ICMI2000，计算机科学讲义 1948，Springer。

K.Inoue: "Optical Recognition of Printes Mathmatical Documents" Proceedings of Third Asian Technology Conference in Mathematics,Springer. 280-289 (1998)

K.Inoue：“打印数学文档的光学识别”第三届亚洲数学技术会议论文集，施普林格。