Dastaan.io – New Platform Launched to Make Urdu Text Editable

The Neurocomputation Lab at the NED University, in collaboration with Anjuman Taraqqi-e-Urdu Pakistan, developed the website www.dastaan.io and its mobile Android app. The platform is able to convert images of printed Urdu text in the Nastaleeq script into editable text for computers and also read them out. It was termed a landmark event in the digitization of the Urdu language in the modern era.

The platform was launched recently by NED University Vice Chancellor Dr. Sarosh Hashmat Lodi at the university’s auditorium. Federal Minister for Religious Affairs Aneeq Ahmed, Anjuman President Wajid Jawad, and Treasurer Syed Abid Rizvi participated in the event.

Currently, the website and app can convert any uploaded image of printed Urdu text into editable text form and read it. However, the project was still not completed, as the developers have plans to add more features to it. The new features include the conversion of Urdu text into Braille for people with vision impairments, along with the development of an iOS app.

The project head, Dr. Majida, said that Urdu is one of the toughest and most complex languages to be digitized owing to its script, in which alphabets keep altering their form based on their position in the word. She explained that the development of any optical character recognition (OCR) system for English or other European languages is comparatively easy as their alphabets were written discretely and not joined into the following alphabets.

Moreover, she said that the Nastaleeq script was also not linear, and words appeared on the line diagonally. Similarly, she said, a few Urdu alphabets were written above the line, while others would go below the line. Because of these factors, it is difficult to program an OCR system for Urdu.

In addition, the project head added that around 300 individuals, including 200 interns, took part in the project, and about 90,000 man-hours were spent on it in a couple of years. She also added that three master’s theses and 20 final-year projects were successfully accomplished on the project, while a candidate was also doing a PhD in it.

Also read:

Google Play Store Removes 111 Fraudulent Micro Loan Apps on PTA’s Request