OCR (Optical Charactor Recognition) is the process of turning a picture of words (such as a scan of a typed letter) into an editable document that you can open and use in your desktop publishing software, word processor, or other text editor. Today's OCR packages contain sophisticated support for multiple languages, PDF and HTML output, and format retention.
This list updated September 2010.
ABBYY FineReader
© ABBYY
The Mac version of their OCR which handles PDF and HTML and retains document formatting is a 2010 Macworld awards winner.
Available as of 2010: FineReader Express Edition for Mac
Nuance OmniPage
OmniPage Pro X for Mac Image Courtesy of PriceGrabber
Formerly from ScanSoft, in addition to OCR that retains formating and includes table formating, it allows the conversion of PDF files to various formats or the conversion of paper documents to PDF. Despeckle Mode improves character recognition for poor-quality originals. Includes Voice Read Back, HTML support, and multiple language support. The newest versions for OmniPage appear to be Windows only. The Mac version is no longer found on the Nuance site so it may be harder to find now.
Available as of 2010: OmniPage Pro X (Version 10) for Mac
Readiris for Mac
Readiris Pro 12 Image courtesy of PriceGrabber
Handles paper and PDF documents in over a hundred languages. Includes PDF and HTML output along with text, RTF, and other formats. The Corporate edition adds more compression levels, unlimited pages of recognition per document. Demo of Pro edition available.
Available as of 2010: Readiris Pro 12 for Mac and Readiris Corporate 12 for Mac
