Improving capabilities for visually challenged person in library environment

Nowadays, there are lot of assistive technologies to support visually impaired people. Among them computer vision based methods provide a feasible solution. An indoor environment provides challenges like object recognition, character and scene recognition. It is important to understand that people feel insecure in places and also when they need to support their people along because of their challenges in vision. It is essential that a technology based solution can be provided to support the people so that they can be guided along in their pathways, rooms, shopping malls. In this paper a model is proposed for detecting text from natural scene video and informing the user through audio to guide visually impaired people in a library. Key frames are extracted based on PSNR and Edge Change Ratio method. Deep learning is used to recognize characters from natural scenes. This paper gives an outline of different innovations which are created lately to extract key frames, recognize text from natural scenes and strategies in unconstrained character acknowledgment which are the various phases of the assisting person with vision challenges.