基于AE-CNN的手势识别算法

HAND GESTURE RECOGNITION ALGORITHM BASED ON AE-CNN

在手势识别的过程中,手势的多样性和复杂程度会对手势识别率造成很大的影响.随着深度学习的快速发展,卷积神经网络在手势识别领域取得了突破性进展.但基于卷积神经网络的方法仍存在收敛速度慢、识别率低等问题,因此手势识别很难取得较好成果.为了解决卷积神经网络在手势识别中存在的收敛速度慢、识别率低问题,提出一种AE-CNN的手势识别算法.实验结果表明,该算法收敛速度快、识别准确率高,并且没有明显增加识别过程的耗时性.

In the process of gesture recognition, the diversity and complexity of gesture greatly influence the recognition rate. With the rapid development of deep learning, the convolution neural network (CNN) has made a breakthrough in the field of gesture recognition. The existing methods based on CNN still have some problems such as slow convergence speed and low recognition rate, so it is difficult to achieve good results in gesture recognition. To solve these problems, this paper proposes an AE-CNN recognition algorithm. The results show that the proposed algorithm has fast convergence speed, high recognition rate, and does not significantly increase the time consumption of the recognition process.