Implementation of a reading device for bengali speaking visually handicapped people

Abstract

A reading device is a compact hardware setup with necessary programmes coded in it which read out printed documents like a human reader. People having eyesight problem can't read books, papers or any kind of printed reading materials. This problem can be solved simply by taking image of the reading materials, extracting words from the image and converting those words to sound, so by hearing that text converted sound they can understand what is written on that paper. A device is implemented for Bengali speaking visually handicapped people. For character recognition tesseract-ocr is used as optical character recognition(OCR) engine. Python gTTS module, a text to speech engine is used to convert the words extracted by tesseract-ocr to sound. Whole process is implemented on Raspberry Pi based a compact hardware design. Accuracy of character detection from the captured image and words to sound conversion is as high as 85 %. It is to be mentioned that accuracy is calculated as percentage of correct words to total words in an image.