Published Paper Details:

Decades ago, visually impaired people faced a lot of challenges in their daily routine. Development and enhancement in technology enabled them to live confidently. Our proposed work consists of camera based assistance for the visually impaired students to improve their academics to read texts from hand held objects in daily routine works. In our proposed system we use OpenCV to filter and recognize characters from texts. This process is framed into three stages. The first stage consists of a mini camera which captures the image and the text is extracted from the image by text recognition algorithm. The second stage consists of the filtered text which is converted to speech as an audio output. The audio output is same as that of normal human speech. The third stage consists of speech to text conversion. The entire application will run on Raspberry-Pi kit. The camera module is used to capture the required image which will be later processed in OpenCv platform by using the OCR, the text will be extracted from the image captured. The audio to text conversion is achieved by means of Google Voice Talks. The text to audio output will be provided using eSpeak.