Graph Element Recognition Networks DAGRN Based on Shuffle Attention and Criss Cross Attention

Graph element recognition, which enables computers to accomplish creative tasks with the help of high-performance computing, is a challenging but promising research direction. So far, how to achieve efficient and accurate graph element recognition is still an area worth exploring in depth. In this paper, by introducing the attention mechanism in YOLOV5, the model is able to efficiently capture the long-distance dependencies among tuples and enhance the attention to key features. In addition, combined with the efficient feature extraction and detection capabilities of YOLOV5, the network improves the accuracy and robustness of the recognition while maintaining the real-time detection speed. The experimental results show that DAGRN achieves excellent performance on the graph element recognition dataset, and the generated recognition results show good accuracy and stability in both subjective and objective evaluation metrics, which verifies the effectiveness and application prospect of the method.