Real-Time Object Recognition with Voice Feedback for Visually Impaired Based on Raspberry Pi

Object Detection is a field of Computer Vision that detects instances of semantic objects in images or videos (by creating bounding boxes around them in our case). In this project, we will convert image to text and then text to speech for the visually impaired person who deserve to live independently by using You Only Look Once V3 (YOLO v3) algorithm that runs through a variation of an extremely complex Convolutional, We can then convert the annotated text into audio responses and give the location of the objects in the camera’s view. The system will continuously capture multiple frames using a camera on raspberry pi and the frames then converted to audio segment, the obtained results manage to achieve the success of the proposed prototype in giving visually impaired users the capability to understand unfamiliar surroundings, through a user friendly device with this profound object identification model.