Design and Development of Cognitive IoT Assistance System for Visually Impaired

In this paper, the problem of object recognition faced by visually impaired people in their daily life is considered. This problem causes them to face problem while crossing road and sometimes land them in the scenario of accident. In the literature different assistive solutions have been proposed to assist the visually impaired people. Some of them are Assistance from stick, Robot Assistance and Assistance by the visually fit people. Assistance from stick helps them to sense the object and also helps them to carry out various activities such as walking, negotiating a crowd and so on, but at the same time they won't know the object that is in front of them. Robots help them to navigate from one place to another, but at the same time it is highly expensive. Assistance from visually fit people is not a viable solution since; nowadays in this busy world people do not find time to help others. Looking at the problems faced by the visually impaired people, an assistive technology solution is being proposed by leveraging Internet of Thing (IoT), Machine Learning and Embedded Technologies for the visually impaired that helps them to move from one place to another without depending on others. The solution employs Google Tensor Flow Machine Learning Framework for the classification of the real-world objects. Therefore, the proposed system can rise the cognizance of the explored environment, it interacts with its user by means of audio messages and at the same time it is a cost-effective solution.