Development of Prototype Spectacles for the Blind with Digital to Voice Conversion Device

This paper addresses a prototype, smart spectacles, designed and developed to facilitate conversion of the words to voice. The Rehabilitative spectacles contain a small camera at the centre point. The characters when written or printed on the paper will be captured by the camera present in spectacles and converts into digital using raspberry pi 3 which is loaded with OCR (Optical Character Recognition) method. After conversion of the data, this information will be passed through a head phones from wifi module in raspberry pi 3. Making this advanced, the digital data can be transmitted at a particular bandwidth range and converting into voice and passing information last through Bluetooth and wifi connected headphones. The spectacles are also instrumented with a pair of ultrasonic transducers mounted centrally above the bridge, and with a buzzer at one of the temples. They are used to detect paper at head level. This detects the paper and converts the character present in the paper and gives output in voice. By running OCR software on such images usually ends with low OCR performance since images can have low resolution, low image quality or colourful background. In order to improve OCR performance, different image pre-processing methods are proposed. This makes more efficient in conversion of digital data into voice. The algorithm for character topology composition has been proposed. The developed system is regarded as a step-forward towards the advancements in Electronic Travel Aids, and should contribute to the betterment of the life of individuals with vision loss.