Machine Learning Based Object Detection and Voice Guidance Using Yolo Algorithm

Machine learning is used now a days in multidiscipline. Vision based or image-based application is very popular in healthcare and human interaction. The proposed model of this article is focus on visually challenged individuals to navigating the environment and ensure their safety by detecting nearby objects using the machine learning algorithm like YOLOV5 model. Secondary module is focus on alert intimation through speech notification. Clear vision is one of the God’s gifts, unfortunately so human is having some issue in their vision, this kind of modern technology will help to solve this issue. This model is mainly help to identify the object at the same time spatial location. Computer vision algorithms, particularly those that leverage convolutional neural networks, are subsequently employed to identify and categorize objects within the scene. The spatial location of these objects is determined, potentially using depth sensors or stereo cameras to calculate distance and relative position. This integration of technology not only aids in recognizing objects but also enhances spatial awareness, contributing to safer and more confident navigation for visually impaired individuals. The average precision level of proposed model is 91% and average Recall value is providing 0.88.