Efficient Conversion of Handwritten Text to Braille Text for Visually Challenged People
The World Health Organization has submitted a report in 2017 which declared that a population of nearly 36 million people are blind out of 253 million visually impaired people. Braille books in the tactile format are very helpful for the visually impaired people to gain knowledge but the availability of these resources is limited. With the improvement of electronic innovation, Braille ended up being appropriate to PC helped generation in light of its coded structures. Programming based content to-Braille interpretation has been ended up being a fruitful arrangement in Assistive Innovation. Various research studies and papers describe the methods for obtaining machine readable document from textual image. In future, character recognition might serve as a key role to create a paperless environment that helps the visually impaired people to gain enormous amount of educational materials. In current world the innovations and advancements in modern scientific systems has expanded the boundaries of human effort like Optical Character Recognition. In the field of machine learning and pattern matching Handwritten recognition has gained lot of attention. A novel method is proposed to convert Handwritten text into Braille text due to which huge resources of Handwritten text materials will be available in Braille text that helps the visually impaired and low vision people to expand their knowledge. The novelty of this system has gained a better accuracy.
KeywordsBraille Handwritten Optical Character Recognition Visually impaired
- 1.Nahar, L., Jaafar, A., Ahamed, E., Kaish, A.B.M.A.: Design of a Braille learning application for visually impaired students in Bangladesh. Off. J. RESNA 27(3), 172–182 (2015)Google Scholar
- 3.Sultana, S., Rahman, A., Chowdhury, F.H., Zaman, H.U.: A novel Braille pad with dual text-to-Braille and Braille-to-text capabilities with an integrated LCD display. In: 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), Kannur, pp. 195–200 (2017)Google Scholar
- 5.Kala, R., Vazirani, H., Shukla, A., Tiwari, R.: Offline handwriting recognition using genetic algorithm. IJCSI Int. J. Comput. Sci. Issues 7(2, 1) (2010)Google Scholar
- 11.Bawane, P., Gadariye, S., Chaturvedi, S., Khurshid, A.A.: Object and character recognition using spiking neural network. In: International Conference on Processing of Materials, Minerals and Energy, vol. 5, no. 1, Part 1, pp. 360–366 (2018)Google Scholar