Reference Guide

Index	Help	Safety

Contents	Glossary

How To

Scan Documents to Convert to Text Data (OCR)

Improve character recognition
Potential text recognition problems

You can scan and convert documents to text data, and then edit them using with a word processing application. The technology that allows computers to "read" text from physical objects is called Optical Character Recognition (OCR). OCR requires a graphical representation of text to interpret, which usually comes from a scanned image.

Follow all of the steps described in For text and line art.

Import the scanned image into the OCR software.

Improve character recognition

Use the Threshold slider to change the threshold value, monitoring the results of the changes in the Preview window. Adjusting the threshold value can make it easier for OCR to recognize characters.

Note:

The Threshold setting is available only when Black&White is selected for Image Type.

You can also select the Text Enhancement check box to improve text scanning (available in Office Mode only).

[Top]

Potential text recognition problems

The quality of the text in your original document greatly affects the OCR results.

The following types of originals can make recognition difficult and should be avoided if possible:

Items that have been copied from other copies

Faxes

Text with tightly-spaced characters or line pitch

Text that is in tables or underlined

Cursive or italic fonts, and font sizes less than 8 points

Remember that OCR software cannot recognize handwritten characters.

[Top]