Optical character recognition

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Optical character recognition (OCR) is a method of automatic data entry. OCR software is used to convert handwritten, type-written or printed text into data that can be edited on a computer. In simple systems, the paper documents are scanned with an image scanner. The OCR software then looks at the image and compares the shapes of the letters to stored images of letters. In this way, it makes a text file that can be edited with a normal text editor.

More complex systems look at images, layout and so on. This can make editable electronic versions which look identical to the original documents.

OCR works best with clean, clearly printed materials.

OCR-Software[change | edit source]