Raspberry Pi based Smart Library for Visually Challenged Citizens

One of the major drawbacks of humanity is visual impairment, particularly information are communicated only by lots of text messages rather than voice communication. The device which is being designed helps the visual impairment of people. In this work, a device which produces speech from the image's text is designed. The fundamental structure in the framework is to extracts the region of in the image that contains text from the captured image and this device converts the extracted text to speech. It Framework is implemented using a camera and a Raspberry Pi system. The image preprocessing steps are done in the captured image to locate the text in the captured image and the preprocessing steps eliminate the image background. Tools like Optical Character Recognition (OCR) and Text to Speech (TTS) engine are used to convert the captured image into speech. Speakers or Earphones are used to hear the audio output from Raspberry Pi.