Smart Vision: Vision For The Visually Impaired

Abstract: Smart Vision is an assistant for blind people which provides the outline of their environment. The smart vision aims to bring the attractive world as a narrative to the visually impaired. The narrative is generated by converting the scenes within their surrounding to text which describes the important objects in the scene. samples of text include 'Children playing within the garden', 'people walking', 'Book kept on the table'. The keywords and one line is played within the variety of audio. Smart vision aims to produce this missing experience for them. The system uses state of the art deep learning techniques from Microsoft Cognitive Services for image classification and tagging. The experience is powered by the python voice assistant.

Keywords: Smart Vision, Deep learning, Microsoft Cognitive Services, image classification, voice assistant, tagging.