A Machine Learning Based Assistant Device for the Blind, Featuring Face and Text Recognition, Distance Measurement, and Location Tracking

Abstract
A Machine Learning Based Assistant Device for the Blind, Featuring Face and Text Recognition, Distance Measurement, and Location Tracking. Our proposed device for the blind is an advancement with the assistance of multidisciplinary subjects like software engineering and hardware designing which will encourage the visually impaired individuals to explore with certainty by recognizing the object, text and person close by. The system incorporates a webcam, GPS and sensors for obstacle avoidance, location tracking, and advanced image processing algorithms for object detection. The system includes an integrated reading assistant, in the form of an image-to-text converter, followed by auditory feedback. For face recognition, we'll use computer-generated filters to transform face images into numerical expressions that can be compared to determine their similarity. These filters are usually generated by using ‘deep learning,’ which will use artificial neural networks to process data. For distance measurement with voice alert, an ultrasonic sensor was used. The sensor will use the waves and the phenomenon of ‘echo’ to detect objects and measure the distance while for sound cues we used an Android phone speaker which was connected via Bluetooth. For location sharing, the system receives information from GPS satellites and obtains the geographical position of the device. Then the GSM module sends an SMS to the number specified in the code. For text, detection computer vision is used in the process of optical character recognition (OCR) to find and read the text in photographs to read newspapers and books. For auditory feedback gTTS API is used to convert text to mp3 format and Playsound is used to play the mp3
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN