OCR

 
Homepage    TextBridge    OmniPage Pro    Notes    Downloads
 

What is OCR?

OCR stands for Optical Character Recognition. Very simply stated, OCR means converting an electronic picture of text (such as a letter) into a form your text-based applications-such as word processors, DTP, spreadsheets, and databases-can use.
 
Technically speaking, OCR products look at a picture of a character and convert it into an ASCII or ANSI character that applications programs can utilize. This conversion process is called recognition.
 

What Scanners Do

Scanners are nothing more than fancy cameras. They simply take a picture of a page, then pass it to the PC in electronic format as a bit-mapped image file. Taking an electronic picture is called scanning.

For graphics applications, an electronic picture is just fine. Using a program like PC Paintbrush", you can easily clip the picture or illustration that you want to put in a report, newsletter, or brochure, for example.

Fax machines include a scanner; they take an electronic picture, then send it over telephone lines. So, if you are using OCR on a fax file, whoever sent the fax has done the scanning for you. What you receive on a fax board is a scanned image which can also be converted to text using OCR.
 

What Scanners Don't Do

Scanners do not give you useable text. That's what OCR is all about.
 

How Do You Buy OCR?

Generally, scanners and OCR are sold separately. Some specialized OCR products have both a scanner and an OCR engine built in. This means that you don't have to buy the components separately. Usually these types of systems are designed for production/high-volume applications and are more expensive than a system where the components are sold separately.

Your volume and throughput requirements will determine the solution most appropriate for you.