Gesture recognition model training method, gesture recognition method and system

Abstract

The invention discloses a gesture recognition model training method, a gesture recognition method and a gesture recognition system. The training method comprises the steps of collecting a gesture picture sample in a plurality of scenes, and performing random cutting on the gesture sample to obtain a new gesture sample, and taking the gesture picture sample and the new gesture sample as a sample set; constructing a light YOLO network, and training the Light YOLO network by utilizing a sample set, and a first light YOLO network is obtained; a selective-dropout layer is added behind each layer ofconvolution layer of a first light YOLO network, and a second light YOLO network is obtained. Training and convergence are carried out on the second light YOLO network by means of the sample set, andthen channel cutting is conducted so as to obtain a gesture recognition model. According to the invention, the detection performance of the network with smaller resolution is improved; the gesture recognition method disclosed by the invention is high in accuracy and good in real-time performance; meanwhile, the system can directly obtain the recognition result from the picture, and end-to-end optimization can be carried out.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and more specifically relates to a gesture recognition model training method, a gesture recognition method and a system. Background technique [0002] As one of the most natural body languages, gestures can be applied in the field of human-computer interaction to make the interaction process more natural. Among them, the recognition of human hands is the focus of current research in the field of human-computer interaction. Scholars at home and abroad have carried out a lot of research on vision-based gesture recognition technology. [0003] Traditional gesture recognition systems generally perform gesture segmentation first to obtain gesture regions, then extract gesture features, and finally use gesture features for classification. Traditional methods require manual design of features, such as color features, HOG features, etc. These features have poor generalization ability, and differ...

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a gesture recognition model training method, gesture recognition method and system, thereby solving the problems of low accuracy and poor real-time performance in the existing gesture recognition methods in complex scenes question

Images