Department of Automation and Applied Informatics Politehnica University Timisoara, Romania.
Stud Health Technol Inform. 2022 Jun 29;295:189-192. doi: 10.3233/SHTI220694.
Static and dynamic gestures are frequently used in activities supporting learning, recovery healthcare, engineering, and 3D games to increase the interactivity between man and machine. The gestures are detected via hardware devices and data is processed using different software methods. This paper presents the manner of detection and interpretation of two gestures, a hand rotation gesture and a palm closing and opening gesture, using the Leap Motion device. These two dynamic gestures are very often used in hand recovery exercises. For comparing the two gestures we use data classification methods, Support Vector Machine (SVM) and Multilayer Perceptron (MLP). The data for the gesture classification were 80% training data and 20% testing data. The metrics for comparison are precision, recall, F1-score, and the total number of testing cases (support). The SVM classifier gives an accuracy of 99.4% and the MLP classifier a 96.2%. We built two confusion matrices for better visualizing the results.
静态和动态手势经常用于支持学习、康复医疗、工程和 3D 游戏的活动中，以增加人机之间的交互性。这些手势通过硬件设备进行检测，并使用不同的软件方法处理数据。本文介绍了使用 Leap Motion 设备检测和解释两种手势的方法，一种是手部旋转手势，另一种是手掌开合手势。这两种动态手势在手部康复练习中经常使用。为了比较这两种手势，我们使用了数据分类方法，支持向量机 (SVM) 和多层感知机 (MLP)。手势分类的数据是 80%的训练数据和 20%的测试数据。比较的指标是精度、召回率、F1 分数和测试用例总数 (支持)。SVM 分类器的准确率为 99.4%，MLP 分类器的准确率为 96.2%。我们构建了两个混淆矩阵，以便更好地可视化结果。
