In this paper, we present an efficient method to incrementally learn to classify static hand gestures. This method allows users to teach a robot to recognize new symbols in an incremental manner. Contrary to other works which use special sensors or external devices such as color or data gloves, our proposed approach makes use of a single RGB camera to perform static hand gesture recognition from 2D images. Furthermore, our system is able to incrementally learn up to 38 new symbols using only 5 samples for each old class, achieving a final average accuracy of over 90\%. In addition to that, the incremental training time can be reduced to a 10\% of the time required when using all data available.

翻译：本文提出一种高效方法，用于增量式学习静态手势分类。该方法允许用户以增量方式教会机器人识别新符号。与采用特殊传感器或外部设备（如彩色手套或数据手套）的其他研究不同，我们的方法仅通过单个RGB摄像头即可从二维图像实现静态手势识别。此外，系统仅需每类旧手势5个样本即可增量学习多达38个新符号，最终平均准确率超过90%。同时，增量训练时间可缩减至使用全部可用数据时所需时间的10%。