The underwater imaging process is often hindered by high noise levels, blurring, and color distortion due to light scattering, absorption, and suspended particles in the water. To address the challenges of image enhancement in complex underwater environments, this paper proposes an underwater image color correction and detail enhancement model based on an improved Cycle-consistent Generative Adversarial Network (CycleGAN), named LPIPS-MAFA CycleGAN (LM-CycleGAN). The model integrates a Multi-scale Adaptive Fusion Attention (MAFA) mechanism into the generator architecture to enhance its ability to perceive image details. At the same time, the Learned Perceptual Image Patch Similarity (LPIPS) is introduced into the loss function to make the training process more focused on the structural information of the image. Experiments conducted on the public datasets UIEB and EUVP demonstrate that LM-CycleGAN achieves significant improvements in Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), Average Gradient (AG), Underwater Color Image Quality Evaluation (UCIQE), and Underwater Image Quality Measure (UIQM). Moreover, the model excels in color correction and fidelity, successfully avoiding issues such as red checkerboard artifacts and blurred edge details commonly observed in reconstructed images generated by traditional CycleGAN approaches.
A lightweight infrared image denoising method based on adversarial transfer learning is proposed. The method adopts a generative adversarial network (GAN) framework and optimizes the model through a phased transfer learning strategy. In the initial stage, the generator is pre-trained using a large-scale grayscale visible light image dataset. Subsequently, the generator is fine-tuned on an infrared image dataset using feature transfer techniques. This phased transfer strategy helps address the problem of insufficient sample quantity and variety in infrared images. Through the adversarial process of the GAN, the generator is continuously optimized to enhance its feature extraction capabilities in environments with limited data. Moreover, the generator structure incorporates structural reparameterization technology, edge convolution modules, and progressive multi-scale attention block (PMAB), significantly improving the model’s ability to recognize edge and texture features. During the inference stage, structural reparameterization further optimizes the network architecture, significantly reducing model parameters and complexity and thereby improving denoising efficiency. The experimental results of public and real-world datasets demonstrate that this method effectively removes additive white Gaussian noise from infrared images, showing outstanding denoising performance.
Pulsed eddy current thermography can detect surface or subsurface defects in steel, but in the process of combining deep learning, it is expensive and inefficient to build a complete sample of defects due to the complexity of the actual industrial environment. Consequently, this study proposes a transfer learning method based on Twin-NMF and combines it with the SimAM attention mechanism to enhance the detection accuracy of the target domain task. First, to address the domain differences between the target domain task and the source domain samples, this study introduces a Twin-NMF transfer method. This approach reconstructs the feature space of both the source and target domains using twin non-negative matrix factorization and employs cosine similarity to measure the correlation between the features of these two domains. Secondly, this study integrates a parameter-free SimAM into the neck of the YOLOv8 model to enhance its capabilities in extracting and classifying steel surface defects, as well as to alleviate the precision collapse phenomenon associated with multi-scale defect recognition. The experimental results show that the proposed Twin-NMF model with SimAM improves the detection accuracy of steel surface defects. Taking NEU-DET and GC10-DET as source domains, respectively, in the ECTI dataset, mAP@0.5 reaches 99.3% and 99.2%, and the detection accuracy reaches 98% and 98.5%.
Underwater images frequently suffer from severe quality degradation due to light attenuation and scattering effects, manifesting as color distortion, low contrast, and detail blurring. These issues significantly impair the performance of downstream tasks. Therefore, underwater image enhancement (UIE) becomes a key technology to solve underwater image degradation. However, existing data-driven UIE methods typically rely on difficult-to-acquire paired data for training, severely limiting their practical applicability. To overcome this limitation, this study proposes MambaRA-GAN, a novel unpaired UIE framework built upon a CycleGAN architecture, which introduces a novel integration of Mamba and intra-domain reconstruction autoencoders. The key innovations of our work are twofold: (1) We design a generator architecture based on a Triple-Gated Mamba (TG-Mamba) block. This design dynamically allocates feature channels to three parallel branches via learnable weights, achieving optimal fusion of CNN’s local feature extraction capabilities and Mamba’s global modeling capabilities. (2) We construct an intra-domain reconstruction autoencoder, isomorphic to the generator, to quantitatively assess the quality of reconstructed images within the cycle consistency loss. This introduces more effective structural information constraints during training. The experimental results demonstrate that the proposed method achieves significant improvements across five objective performance metrics. Visually, it effectively restores natural colors, enhances contrast, and preserves rich detail information, robustly validating its efficacy for the UIE task.
As the core equipment of the high-pressure diaphragm pump, the working conditions of the check valve are complicated, and the vibration signal generated during operation displays non-stationary and nonlinear characteristics. In order to accurately describe the non-linear dynamics of the check valve, the smoothing prior analysis (SPA) method is used to decompose the vibration signal of the check valve, obtain the tendency term and fluctuation term components, and calculate the frequency-domain fuzzy entropy (FFE) of the component signals. Using FFE to characterize the operating state of the check valve, the paper proposes a kernel extreme-learning machine (KELM) function norm regularization method, which is used to construct a structurally constrained kernel extreme-learning machine (SC-KELM) fault-diagnosis model. Experiments demonstrate that the frequency-domain fuzzy entropy can accurately characterize the operation state of check valve, and the improvement of the generalization of the SC-KELM check valve fault model improves the recognition accuracy of the check-valve fault-diagnosis model, with an accuracy rate of 96.67%.