A Convolutional Neural Network based Live Object Recognition System as Blind Aid

TL;DR

This paper presents a real-time object recognition system using CNNs to assist visually impaired individuals by identifying objects through a camera and providing audio or Braille feedback, enhancing safety and independence.

Contribution

It introduces a CNN-based live object recognition system specifically designed as a blind aid, integrating real-time detection with accessible output methods.

Findings

Achieved real-time object detection with CNN on pre-trained ImageNet models

Provided accessible output via audio and Braille for visually impaired users

Demonstrated system's potential to improve safety and independence

Abstract

This paper introduces a live object recognition system that serves as a blind aid. Visually impaired people heavily rely on their other senses such as touch and auditory signals for understanding the environment around them. The act of knowing what object is in front of the blind person without touching it (by hand or some other tool) is very difficult. In some cases, the physical contact between the person and object can be dangerous, and even lethal. This project employs a Convolutional Neural Network for recognition of pre-trained objects on the ImageNet dataset. A camera, aligned with the system's predetermined orientation serves as input to the computer system, which has the object recognition Neural Network deployed to carry out real-time object detection. Output from the network can then be parsed to present to the visually impaired person either in the form of audio or Braille text.