Abstract:
In the running world, there is developing need and urge for the systems which help to perceive characters or traits in computer when useful data is screened through physical printed paper books/records as we understand that we have a number of daily papers, books and articles which are in hard back or printed structure. In these modern and advancement times there is a huge demand in putting away the details or data useful in these paper archives into a digitized form i.e. in computer memory and when needed, utilizing the data. OCR for the Urdu language is being made for digitizing the hard-back physical Urdu text and later have the ability to edit the digital data. OCR is a worldwide strategy planned for recognizing text in pictures. It converts or changes over manually written, self-made or printed text into data that can be altered by a client on a PC. We are proposing making an OCR software for Urdu that would convert Urdu text in pictures into an editable content document. Machine-readable text would then be decoded by screen readers, tools and apps that use text to audio feature so to read out the words on a screen so visually impeded individuals can be able to understand what’s written on the print out.
