Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps
Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps
复制标题
DOI：
10.3390/app11041933
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
H. Hikawa;Yuta Ichikawa;Hidetaka Ito;Y. Maeda
中科院分区：
文献类型：
--
作者：
H. Hikawa;Yuta Ichikawa;Hidetaka Ito;Y. Maeda
本文提出了一种具有手势识别功能的实时动态手势识别系统。在所提出的系统中，输入视频帧被转换为特征向量，并且它们被用来形成表示输入手势的姿势序列向量。然后，在自组织映射（SOM）-Hebb分类器中进行手势识别和手势定位。手势识别功能通过使用姿势序列向量与赢家神经元的权重向量之间的向量距离来检测手势的结束。通过仿真和实时手势识别实验对所提出的手势识别方法进行了验证。结果表明，该系统可以识别九种类型的手势，准确率为96.6%，并成功地输出识别结果的手势结束时使用的定位结果。
In this paper, a real-time dynamic hand gesture recognition system with gesture spotting function is proposed. In the proposed system, input video frames are converted to feature vectors, and they are used to form a posture sequence vector that represents the input gesture. Then, gesture identification and gesture spotting are carried out in the self-organizing map (SOM)-Hebb classifier. The gesture spotting function detects the end of the gesture by using the vector distance between the posture sequence vector and the winner neuron’s weight vector. The proposed gesture recognition method was tested by simulation and real-time gesture recognition experiment. Results revealed that the system could recognize nine types of gesture with an accuracy of 96.6%, and it successfully outputted the recognition result at the end of gesture using the spotting result.