Artificial Eye for the Blind

TL;DR

This paper presents an integrated assistive device called Artificial Eye for the blind, combining sensors, object detection, OCR, and voice assistance on a Raspberry Pi to aid visually impaired users in navigation and information access.

Contribution

It introduces a low-cost, multi-functional assistive system integrating obstacle detection, object recognition, text reading, and voice interaction on a Raspberry Pi platform.

Findings

Effective obstacle detection within specified range

Successful text extraction from images using OCR

Real-time object and text recognition with voice feedback

Abstract

The main backbone of our Artificial Eye model is the Raspberry pi3 which is connected to the webcam ,ultrasonic proximity sensor, speaker and we also run all our software models i.e object detection, Optical Character recognition, google text to speech conversion and the Mycroft voice assistance model. At first the ultrasonic proximity sensor will be measuring the distance between itself and any obstacle in front of it .When the Proximity sensor detects any obstacle in front within its specified range, the blind person will hear an audio prompt about an obstacle in his way at a certain distance. At this time the Webcam will capture an image in front of it and the Object detection model and the Optical Character Recognition model will begin to run on the Raspberry pi. The imat of the blind person. The text and the object detected are conveyed to the blind pege captured is first sent through the Tesseract OCR module to detect any texts in the image and then through the Object detection model to detect the objects in fronrson by converting the texts to speech by using the gTTS module. Along with the above mentioned process going on there will be an active MYCROFT voice assistant model which can be used to interact with the blind person. The blind person can ask about the weather , daily news , any information on the internet ,etc