使用新颖无菌训练技术，在深度卷积神经网络上改进静态手势分类（英文版）

英文标题：Improved Static Hand Gesture Classification on Deep Convolutional Neural Networks using Novel Sterile Training Technique中文摘要：本文通过引入 “无特征” 的图像以区分手势的不同特征，并使用卷积神经网络和毫米波雷达等新的数据采集和训练技术，提高静态手势识别的分类准确率，从而将手势的分类准确率从 85% 提高到 93% 和从 90% 提高到 95%。英文摘要：In this paper, we investigate novel data collection and training techniquestowards improving classification accuracy of non-moving (static) hand gesturesusing a convolutional neural network (CNN) andfrequency-modulated-continuous-wave (FMCW) millimeter-w