PORTABLE TEXT TO SPEECH DEVICE FOR VISUALLY IMPAIRED USING RASPBERRY PI AND WEBCAM
Siva Rama Krishna, Sourabh Kumar, Jayendra Kumar · Journal of Emerging Technologies and Innovative Research · 2019
Communication plays a major role in human life. Vision has one of the utmost importance in making the communication complete. A person needs vision to access information from a text or image. Visually impaired people gather information from voice only. In many situations, information access for those people is very difficult due to their disability. The proposed paper here implements an idea for image conversion to speech with the help of Raspberry Pi, a Web cam and a speaker or an earphone. The proposed idea uses the concept of Tesseract OCR (Optical Character Recognition) to produce speech from image captured by the camera. This helps the visually impaired people to access the information of text in printed materials i.e. books as well as hand-written notes. The implemented prototype will be a portable device since a power bank is used for its battery backup and gives speech output in multiple languages with the help of Speech API and Microsoft translator. This idea can help millions of visually impaired people to get vision experience and helps them a lot for reading, shopping, indoor and outdoor navigation.