Object Detection For Visually Impaired
Raj Rohit Singh, Laksh Jethani, Shubh Sanghvi, Ratnesh Patil, Nabanita Mandal · 2023
In this project, we are evaluating the efficacy of utilizing deep learning and convolutional neural networks to support individuals who have visual disabilities. Our objective is to create a mobile or web application that aids people with visual impairments in their daily activities by assisting them in recognizing objects within their proximity. This application leverages recent advancements in machine learning, particularly deep learning in conjunction with transfer learning. By employing convolutional neural networks, the approach becomes less reliant on specific characteristics. The process begins by capturing an image or video through the camera. The algorithm identifies the objects present and transmits the anticipated object names to text-to-speech software. Subsequently, this software converts the names into auditory output, providing a means for visually impaired individuals to perceive the information.