Gesture Recognition Machine Vision Video Calling Application Using YOLOv8

Gesture recognition pertains to a computer system’s capacity to identify and understand hand gestures, categorizing them into captions or text. This technology holds vast potential for applications in education, communication, and accessibility, especially for individuals with hearing disabilities. This research introduces a gesture recognition video calling application, enabling communication among individuals with and without speech and hearing abilities. To enhance accuracy, the application employs Darknet’s YOLOv8 for object detection. YOLOv8 is a robust and efficient system that excels in various computer vision tasks, such as object detection, instance segmentation, and image classification. The paper proposes a trained model for image classification, encompassing ten different hand gesture classes, which processes each video frame during the call, achieving a remarkable 98% accuracy with a low latency of 10ms. The application displays the classification results on top of the interface during the video call.