What Is OCR? |
|
Answer:
OCR is short for Optical Character Recognition. This type of system is used in order to convert paper books and documents into electronic files, such as computerizing an old record keeping system in an office or to convert old out of print books into e-books. Normally when you scan a page into a computer, the scanner will produce an image file, or in other words, a photo of the page. In this form, the page is not searchable, and the computer cannot understand the letters on the page. Ad far as the computer is concerned, it cannot tell the difference between the scanned page and a photo from your wedding. OCR software is then used to convert the scanned page into a text or word processor file in order to allow you to search, edit, and format the text. Optical character recognition and digital character recognition were once separate fields, but now they have merged into a single field as technology has advanced. Early systems had to be trained in order to read a specific font, and they had to be fed images of each letter. Now, more intelligent systems are available which are able to do a lot of this on their own. These systems are not foolproof, however, as they do make mistakes and pages should be proof read before assuming that everything translated correctly. Trackback(0)
Comments (0)
![]() Write comment
You must be logged in to post a comment. Join for free or Login.
|
Save or Share