19-09-2014, 02:01 PM
Abstracts: • OCR (Optical Character Recognition) is a technology that transforms the characters stored into image in the pixel form into text form. • OCR is designed to simplify character recognition. It can do conversion of scanned image of typewritten or printed text into machine encoded text. It is a common method of digitizing printed text so they can be electrically searched, it can be used for cut, copy, paste. • If the characters are in the image then we can’t perform operation directly but by using OCR it can be directly converted into text form. • OCR is a field of research in pattern recognition (font recognition) .OCR can be used to reduce cost for data entry, secure document processing (checks, financial documents, bills).OCR can be used for more quickly make textual version of printed document, e.g. book scanning, Line Removal which cleans up non glyph boxes and lines (ex. If the text in the box or line (underline) it can be removed). It can be also used for sorting such that we can sort the string which is in form of characters and manage it in such specific order like ascending or descending order. We can extend the feature like making text to speech conversion so the text can be crosschecked.