To effectively solve the problems of feature omission and low efficiency of feature information utilization in convolutional neural networks,this article proposes a static gesture recognition method based on an improved residual network.In the Residual Network(ResNet)model,residual blocks were improved,the model was optimized,and the feature extraction ability and training stability of the model were enhanced.The experimental results show that compared with the traditional ResNet34 model,the improved ResNet model has better performance and can improve the recognition accuracy of gesture images.
维普
万方数据