Skip to content
Skip to main content

About this free course

Download this course

Share this free course

Crossing the boundary: analogue universe, digital worlds
Crossing the boundary: analogue universe, digital worlds

Start this free course now. Just create an account and sign in. Enrol and complete the course for a free statement of participation or digital badge if available.

4.2.5 Scanners and OCRs

A better solution is to get some electronic help. A page of text is placed in a scanner, which produces an image of the page using techniques that I will discuss shortly. The image is passed to a computer program called an optical character recogniser (OCR), which detects each letter on the page in turn and transforms it into its digital code. This recognition is an immensely difficult task, requiring very sophisticated software, so OCRs are generally only partially effective.


Why do you think recognising characters is such a difficult task for a machine?


Because the same character can be presented in many different forms.

We need to remember that computers are very simple-minded devices. We have no difficulty in recognising that

are all the same character. But a computer will interpret two images with even the smallest difference between them as completely separate things. Clever software has to be devised to tackle this problem.