Audio Narration of a Scene for Visually Disabled using Smart Goggle: An Implementation Survey
Keywords:
Raspberry Pi, TensorFlow, TensorFlow Lite, OpenCV, Convolution Neural Network, Text to Speech (TTS) engine, Object detection, Long Short-Term Memory (LSTM), Recurring Neural NetworkAbstract
Blindness is one of the major problems in our society which made it difficult t for a blind person to lead their day-to-day life. Due to the loss of sight, many information about the real-world scenarios and surroundings will be missed for blind people. By using various multimedia information processing methods and technologies, our device will first acquire the image information through either Pi camera or Webcam, then performs and image to text conversion. Then the blind person is directed through voice commands generated by the application according to the object detection. Before only text reading system was there. But in this approach our Smart Goggle system will detect, track and analyze the approaching objects and give information about them. This will help the blind people to get more information access about real world and reduces numerous difficulties faced by them.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Pratyush Pratap Singh, Sharath S. Hegde, R. Varun, Vivek Hegde, K. A. Sumithra Devi
This work is licensed under a Creative Commons Attribution 4.0 International License.