Currently, gesture recognition is like a problem of feature extraction and pattern recognition, in which a movement is labeling as belonging to a given class. A gesture recognition system’s response could solve different problems in various fields, such as medicine, robotics, sign language, human–computer interfaces, virtual reality, augmented reality, and security. In this context, this work proposes a systematic literature review of hand gesture recognition based on infrared information and machine learning algorithms. This systematic literature review is an extended version of the work presented at the 2019 ICSE conference. To develop this systematic literature review, we used the Kitchenham methodology. This systematic literature review retrieves information about the models’ architectures, the implemented techniques in each module, the type of learning used (supervised, unsupervised, semi-supervised, and reinforcement learning), and recognition accuracy classification, and the processing time. Also, it will identify literature gaps for future research.

目前，手势识别就像一个特征提取和模式识别的问题，其中一个动作被标记为属于给定的类别。手势识别系统的响应可以解决各个领域的不同问题，例如医学、机器人、手语、人机界面、虚拟现实、增强现实和安全。在此背景下，这项工作提出了基于红外信息和机器学习算法的手势识别的系统文献综述。这篇系统性文献综述是 2019 年 ICSE 会议上发表的工作的扩展版本。为了开发这个系统的文献综述，我们使用了 Kitchenham 方法。这篇系统的文献综述检索了有关模型架构、每个模块中实施的技术、使用的学习类型（监督、无监督、半监督和强化学习）、识别准确度分类和处理时间。此外，它将确定未来研究的文献空白。