Machine-Learning-Based Device for Visually Impaired Person

Abstract

The blind-assistive devices promote the detection of objects and alerting the user by a buzzer or an alarm. In this project, a camera is placed inside a cap which is used by the visually impaired person. The machine-learning algorithm is used for accurate detection of the object and provides an alarm. The ultrasonic sensor is used to measure the distance between the visually impaired person and the real-time object detected when the object is detected the alarm is actuated. Nowadays, the assistive devices include the involvement of both hardware and software section to assist the blind user. The proposed method for the visually impaired person aims to detect the object more accurately so that the visually impaired person can navigate to their full potential in real-time application.