Optical Character Recognition

Technology that allows letters present on images to be recognized and converted into text files. The most common application of this technology on PCs is to convert the text captured from a magazine or book through a scanner into a text file. The scanner captures the magazine or book page into a graphic file format (Tif, Jpeg, Bmp, etc), which makes it impossible to edit the text contained on this page; you can only edit it as a graphic file. Running an OCR software it will recognize the letters present on the image and will return a text or Word file, for example, allowing you to save it as a txt or doc file, allowing you to edit it.

The recognition is never 100% perfect, since each book, newspaper or magazine use a different kind of letter (font). One trick is to send the recognized text to your word processor and from there you can run a spell check to fix the words that weren’t recognized correctly.