Extraction of Logical Structure from Articles in Mathematics

摘要

We propose a mathematical knowledge browser which helps people to read mathematical documents. By the browser printed mathematical documents can be scanned and recognized by OCR (Optical Character Recognition). Then the meta-information (e.g. title, author) and the logical structure (e.g. section, theorem) of the documents are automatically extracted. The purpose of this paper is to show the extraction method of logical structure specialized for mathematical documents. We implemented this method in INFTY which is an integrated OCR system for mathematical documents. In order to show the effectiveness of the method we made a correct database from an existing mathematical OCR database, and made an experiment.