Gesture Recognition Method Based on Attention Mechanism for Complex Background

Abstract

Human-computer interaction technology is still an unaccomplished goal due to complex background and changeable lighting conditions. A two-stage gesture recognition method is proposed to improve the accuracy of gesture recognition. The first stage combines attention mechanism and atrous spatial pyramid pooling (ASPP) which aims to segment gesture from complex background. The second stage uses a two stream convolutional neural network, combines features from the original picture and the output of the first stage, aims to realize the classification of gestures. It can recognize gestures more accurately compared with other gesture recognition methods.