With advances in technology, motion sensing has been applied in a wide range of devices. The system used for motion sensing captures images via a camera and analyzes the acquired images, also known as human–computer interaction, wherein gesture-controlled machines are considered as the most convenient kind and are most commonly used. However, the existing gesture recognition algorithm often has a long computation time and uses a huge amount of memory, preventing the algorithm from being implemented in embedded systems. To alleviate these problems, in this paper, we propose to reduce the computation time of the system by employing the lifting-based discrete wavelet transform (DWT). The different frequency bands featured in a lifting-based discrete wavelet can swiftly distinguish the face region from the hand region, reduce the image resolution, and thus reduce memory usage. In addition to recognizing gestures in a swift and accurate manner, the gesture recognition approach proposed in this study is also compatible with embedded systems. Our experimental results suggest that the proposed approach can reduce the execution time by up to 66% while achieving a high identification rate.