Object Detection and Narrator for Visually Impaired People

Machine Learning has gained attention since the introduction of high computing machines and the availability of huge amount of data also known as big data. Today, machine learning is used in many types of industries from medical image processing to autonomous car. Detecting objects in images has also become one of the important research areas and now computers are able to not only detect objects but also able to draw bounding boxes on it. This is also known as computer vision. In this paper, we proposed the implementation of computer vision machine learning algorithms to detect object and use it to aid visually impaired and blind persons. This paper explain how convolution neural network are trained on ImageNet dataset that can detect objects and narrate detected objects information to the visually impairs person. This implementation can be used with any device using a camera that includes computers, tablets and mobile phones.