NUANCE OMNIPAGE PRO 6 - REFERENCE MANUAL FOR WINDOWS Reference Manual page 16

What is Optical Character Recognition (OCR)?
Optical character recognition (OCR) is the process of converting an image
file to editable text or graphics. An image is an electronic picture of text
and/or graphics. You acquire an image in two ways:
• By scanning a hard-copy document
• By loading an image file such as a TIFF or PCX file (for example, a
received fax file can be saved to an image-file format and
recognized in OmniPage)
The image you scan or load is at first just a "picture" to your computer
even if it contains text. You can see the text but you cannot edit it. You need
to perform OCR to turn the image into individual characters.
During OCR, OmniPage looks for and defines characters on the image to
produce editable text. You can export the recognized text from OmniPage
to a variety of word-processing, page layout, and spreadsheet programs.
OCR is also referred to as text or page recognition, or just recognition.
The OCR Process
OCR is a three-step process: acquiring an image, zoning the image, and
recognizing the image. Use the process buttons in the toolbar (or
corresponding commands in the Process menu) to set up the OCR process.
The Process Buttons
Each of the following three buttons represents one step in the optical
character recognition (OCR) process.
Image button
Using the Process Buttons
The OCR process offers choices at each step:
1 Loading an image into OmniPage
• Select Scan Image in the Image button's drop-down list to scan in
• Select Load Image to import a graphic-format file such as TIFF or
Zone button
a hard-copy document with a scanner.
PCX.
What is Optical Character Recognition (OCR)?
OCR button
Tutorials 16