If the complex structure of a paper document is not reproduced

Before running the OCR process, the Indexing Station analyzes the logical structure of the document and detects areas containing text, pictures, tables, and barcodes. The program then relies on this analysis to identify which parts of the image need to be recognized and the order in which they should be recognized. This information helps recreate the formatting of the original document.

By default, the Verification Station will analyze documents automatically. In the case of very complex layouts, the program may occasionally make mistakes when determining the type of an area type or locating its borders. It is often easier to correct faulty areas manually rather than drawing all the areas anew.

Use the following tools and commands to correct areas:

  • The manual area adjustment tools available on the toolbar at the top of the Image pane.
  • The shortcut menu commands that can be accessed by right-clicking an area in the Image pane or in the Zoom pane.
  • Commands available on the Area menu.

Make sure you recognize the document again after making the desired adjustments, so that the changes you have made to the areas are reflected in the recognized text.

For more information about areas, see Editing areas.

OCR settings, area properties, and selected saving options will also have an effect on how well the layout of the original document is retained. See also: Editing area properties, Saving OCR results.

29.11.2022 17:26:42

Please leave your feedback about this article

Usage of Cookies. In order to optimize the website functionality and improve your online experience ABBYY uses cookies. You agree to the usage of cookies when you continue using this site. Further details can be found in our Privacy Notice.