Automatic table detection method and system

作者: James R. Stinger

DOI:

关键词:

摘要: A method for automatically detecting table data in a document that is described by page definition language and converting the into markup representation. The may have one or more pages. description of provides list words, position each on with respect to predetermined reference point, size word. present invention identifies utilizing table-identifying features. first feature be number word clusters line. second vertical alignment between lines. third changes text density space