The analysis of corrosion images is crucial in materials science, where acquiring clear images is fundamental for subsequent analysis. The goal of deblurring metal corrosion images is to reconstruct clear images from degraded ones. To the best of our knowledge, this study introduces the first paired blurry-sharp image dataset specifically designed for the metal corrosion domain, filling a critical gap in the existing research. This innovative approach effectively addresses the unique challenges associated with deblurring metal corrosion images. We propose a novel metal corrosion images deblurring network (MCIDN) that employs a dual-domain attention mechanism, integrating both spatial and frequency domains to enhance image clarity. This innovative approach effectively addresses the unique challenges associated with deblurring metal corrosion images. While self-attention is widely used in visual tasks, its quadratic complexity often leads to high computational costs. To address this issue, we introduce a new spatial channel attention module (SCAM) that employs dynamic group convolutions to achieve self-attention, effectively integrating information from local regions and enhancing representation learning capabilities. Recognizing the critical role of frequency components in image restoration, we develop a frequency channel attention module (FCAM) that selectively focuses on different frequency components of images, thereby enhancing deblurring performance. These two attention modules are seamlessly integrated into our network. Compared to existing methods, our approach demonstrates superior performance on datasets of blurry metal corrosion images, achieving a peak signal-to-noise ratio (PSNR) of 32.8645 dB and a structural similarity (SSIM) of 0.9768. These metrics indicate that our method provides clearer and more detailed reconstructions, significantly enhancing the image quality.
Extracting relational triples from unstructured text is essential for information extraction and knowledge graph construction, but it remains challenging in complex scenarios involving overlapping entities and diverse relational patterns. To address this issue, this paper proposes an Information-Enhanced Multi-Scale Fusion Convolutional Neural Network (EnInfo-Mulscal FCNN) for joint entity–relation extraction. The model uses BERT to obtain contextual representations, predicts candidate relations through multi-label classification, incorporates relation-aware features into entity recognition, and introduces a multi-scale fusion convolutional module and an attention-based entity filtering mechanism to enhance subject–object correspondence modeling. Experiments on the NYT-star and WebNLG datasets demonstrate the effectiveness of the proposed method. Experiments show that EnInfo-Mulscal FCNN achieves precision, recall, and F1-score values of 87.2%, 75.1%, and 80.7% on NYT-star and 86.3%, 88.3%, and 87.3% on WebNLG, respectively. Compared with ETL-span, our model improves the F1-score by 2.7% on NYT-star and 4.2% on WebNLG. Compared with PRE-span, our model improves the F1-score by 4.3%, demonstrating its effectiveness in relational triple extraction. These results indicate that the proposed method improves relational triple extraction by enhancing information in the relation identification, entity recognition, and entity filtering stages, thereby improving triple generation in complex text scenarios.