Double Decision Method for Static Gesture Based on Fully Convolutional Networks

This paper proposes a static gesture recognition method based on Fully Convolutional Networks (FCN). By studying the Characteristics of Classic Static Gesture Image and its FCN Segmentation Characteristics, the double decision algorithm of the method is realized by the utilization of both category and shape information in the FCN segmentation results. The method also includes a data augmentation algorithm which can effectively improve the generalization ability of the model. The experimental results show that the method achieves a win-win situation of accuracy and robustness.