<p>Convolutional neural networks (CNNs) continue to present challenges in the form of redundant network architectures, high computational intensity, and difficulties in deployment on an expanding array of embedded devices for the practical task of multi-country currency image recognition. This paper proposes a new lightweight multinational banknote recognition model, designated CA-DSC-RepVGG. The backbone network employs the RepVGG-A0 network, and a lightweight CA coordinate attention mechanism is introduced after the residual structure of the backbone network. This enhances the feature extraction capability by emphasizing the information representation. Concurrently, the conventional convolution in the residual structure is enhanced through the utilization of depth-separable convolution. Subsequently, the CA-DSC-RepVGG model is deployed to the rk3568 embedded device. A series of comparative experiments were conducted on three contemporary banknote image datasets: Australian Dollar, Euro, and US Dollar. The experimental results demonstrate that CA-DSC-RepVGG enhances accuracy by 1.05% and reduces the number of parameters by 78.4% in comparison with the pre-improvement period. Following deployment on rk3568 for testing purposes, the average accuracy value was found to be 99.79%. The single image inference process took approximately 9.83&#xa0;ms, while the detection speed was approximately 101.73 f/s. These results demonstrate that the system meets the requirements for real-time and embedded device deployment of multi-country banknote algorithms in industrial applications.</p>