A comparison of machine learning algorithms applied to hand gesture recognition
A comparison of machine learning algorithms applied to hand gesture recognition
复制标题
应用于手势识别的机器学习算法比较
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Luis Paulo Reis
中科院分区：
文献类型：
--
作者：
P. Trigueiros;F. Ribeiro;Luis Paulo Reis
用于人机交互的手势识别是计算机视觉和机器学习的一个活跃研究领域。手势识别研究的主要目标是创建一个系统，该系统可以识别特定的人类手势并使用它们来传达信息或用于设备控制。本文提出了一个比较研究的四种分类算法的静态手势分类使用两个不同的手特征数据集。所使用的方法包括识别每帧中的手像素，提取特征并使用这些特征来识别特定的手姿势。所获得的结果证明，人工神经网络有一个非常好的性能和特征选择和数据准备是一个重要的阶段，在所有的过程中，当使用低分辨率的图像，如在目前的工作中获得的相机。
Hand gesture recognition for human computer interaction is an area of active research in computer vision and machine learning. The primary goal of gesture recognition research is to create a system, which can identify specific human gestures and use them to convey information or for device control. This paper presents a comparative study of four classification algorithms for static hand gesture classification using two different hand features data sets. The approach used consists in identifying hand pixels in each frame, extract features and use those features to recognize a specific hand pose. The results obtained proved that the ANN had a very good performance and that the feature selection and data preparation is an important phase in the all process, when using low-resolution images like the ones obtained with the camera in the current work.