AUTHOR=Zhijun Guo , Weiming Luo , Qiujie Chen , Hongbo Zou TITLE=Terminal strip detection and recognition based on improved YOLOv7-tiny and MAH-CRNN+CTC models JOURNAL=Frontiers in Energy Research VOLUME=Volume 12 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2024.1345574 DOI=10.3389/fenrg.2024.1345574 ISSN=2296-598X ABSTRACT=For substation secondary circuit terminal strip wiring, low efficiency, less easy fault detection and inspection, and a variety of other issues, this study proposes a text detection and identification model based on improved YOLOv7-tiny and MAH-CRNN+CTC terminal line. First, the YOLOv7-tiny target detection model is improved by the introduction of the attention mechanism SimAM and the Weighted Bidirectional Feature Pyramid Network (BiFPN). This also improves the model's feature enhancements and feature fusion ability, balances the various scales of characteristic information, and increases the positioning accuracy of the text test box. Then, a multi-head attention mechanism (MAH) was implemented to optimize Convolutional Recurrent Neural Network with Connectionist Temporal Classification(CRNN+CTC) so that the model could learn data features with larger weights and increase the model's recognition accuracy. The findings indicate that the enhanced YOLOv7-tiny achieves 97.39%, 98.62%, and 95.07% in terms of precision, recall, and mAP on the detection dataset. The improved MAH-CRNN+CTC model achieved 91.2% character recognition accuracy in the recognition dataset.