Research on Gesture Recognition and Classification Based on Attention Mechanism

Since the 20th century, the computer field has developed rapidly and human-computer interaction has become more and more frequent. As an important development area of human-computer interaction, gesture recognition research is in line with the development needs of today's intelligent society. In this paper, the static gesture data set is used as the research object, and the ResNet in convolutional neural network is used to train it, and the CBAM attention mechanism is introduced to conduct comparison experiments and ablation experiments. The final experimental results show that the ResNet model based on the attention mechanism improves the accuracy of gesture recognition and classification by about 2.5% compared to the ResNet model without the attention mechanism, and both models achieve high accuracy on the dataset, confirming the necessity and effectiveness of the method of introducing the attention mechanism.