Android-Based Object Recognition Application for Visually Impaired

EasyChair Preprint 6043

Abstract

Detecting objects in real-time and converting them into an audio output is a challenging task. Recent advancement in Computer Vision has allowed the development of various real-time object detection applications. This paper describes a simple android app that will help visually impaired people understanding their surroundings. The information about the surrounding environment is captured through a phone camera where real-time object recognition through TensorFlow’s Object Detection API is done. The detected objects are then converted into an audio output using Android’s Text to Speech Library. Tensorflow Lite makes the offline processing of complex algorithms simple. The overall accuracy of the proposed system is found to be approximately 90%

Keyphrases: Android, TensorFlow, TensorFlow Lite, computer vision, machine learning, object recognition

@booklet{EasyChair:6043,
  author    = {Akilesh Salunkhe and Manthan Raut and Shayantan Santra and Sumedha Bhagwat},
  title     = {Android-Based Object Recognition Application for Visually Impaired},
  howpublished = {EasyChair Preprint 6043},
  year      = {EasyChair, 2021}}