Global structure and local detailed texture have different effects on image enhancement tasks. However, most existing works treated these two components in the same way, without fully considering the characteristics of the global structure and local detailed texture. In this work, we propose a structure-texture aware network (STANet) that successfully exploits structure and texture features of low-light images to improve perceptual quality. To construct STANet, a fine-scale contour map guided filter is introduced to decompose the image into a structure component and a texture component. Then, structure-attention and texture-attention subnetworks are designed to fully exploit the characteristics of these two components. Finally, a fusion subnetwork with attention mechanisms is utilized to explore the internal correlations among the global and local features. Furthermore, to optimize the proposed STANet model, we propose a hybrid loss function; specifically, a color loss function is introduced to alleviate color distortion in the enhanced image. Extensive experiments demonstrate that the proposed method improves the visual quality of images; moreover, STANet outperforms most other state-of-the-art approaches.

Two key challenges exist in high dynamic range (HDR) imaging from multiexposure low dynamic range (LDR) images for dynamic scenes: 1) aligning the input images with large-scale foreground motions and 2) recovering large saturated regions from a limited number of input LDR images. To tackle these challenges, several deep convolutional neural networks have been proposed that have made significant progress. However, these methods tend to suffer from ghosting and saturation artifacts when applied to some challenging scenes. In this article, we propose an end-to-end deformable HDR imaging network, called DHDRNet, which attempts to alleviate these problems by building an effective aligning module and adopting self-guided attention. First, we analyze the alignment process in the HDR imaging task and correspondingly design a pyramidal deformable module (PDM) that aligns LDR images at multiple scales and reconstructs aligned features in a coarse-to-fine manner. In this way, the proposed DHDRNet can handle large-scale complex motions and suppress ghosting artifacts caused by misalignments. Moreover, we adopt self-guided attention to reduce the influence of saturated regions during the aligning and merging processes, which helps suppress artifacts and retain fine details in the final HDR image. Extensive qualitative and quantitative comparisons demonstrate that the proposed model outperforms the existing start-of-the-art methods and that it is robust to challenging scenes with large-scale motions and severe saturation. The source code is available at: https://github.com/Tx000/DHDRNet .

Error diffusion algorithm shows great potential in binary defocusing fringe projection profilometry (FPP) for improving the intensity representation of binary patterns. However, the fixed kernel in the error diffusion algorithm makes the generated binary patterns far from optimal patterns because of ignoring the structural differences of patterns and the intensity error induced by the coupling effect among binary patterns. This paper proposes a flexible error diffusion algorithm with an unfixed kernel to generate high-quality binary patterns for binary defocusing FPP, thereby realizing the rapid and accurate 3D shape reconstruction. Dual-objective functions are adopted in the proposed approach for kernel optimization. First, taking the minimum intensity error as one objective, this work presents an unfixed four-coefficient error diffusion algorithm to generate binary patterns with the best intensity representation. Second, taking the minimum phase error as another objective, a dual-objective error diffusion algorithm is developed to select the binary patterns with the best phase quality in the phase domain. Finally, a local intensity correction procedure eliminates phase jump errors in the encoding phase of the selected binary patterns to get the optimal projections for binary defocusing FPP. Simulated and experimental results verify that the binary patterns generated using the proposed approach can support the accurate binary defocusing FPP at various degrees of defocusing.

It is difficult to detect and identify natural defects in welded components. To solve this problem, according to the Faraday magneto-optical (MO) effect, a nondestructive testing system for MO imaging, excited by an alternating magnetic field, is established. For the acquired MO images of crack, pit, lack of penetration, gas pore, and no defect, Gaussian filtering, bilateral filtering, and median filtering are applied for image preprocessing. The effectiveness of these filtering methods is evaluated using metrics such as peak signal–noise ratio (PSNR) and mean squared error. Principal component analysis (PCA) is employed to extract column vector features from the downsampled defect MO images, which then serve as the input layer for the error backpropagation (BP) neural network model and the support vector machine (SVM) model. These two models can be used for the classification of partial defect MO images, but the recognition accuracy for cracks and gas pores is comparatively low. To further enhance the classification accuracy of natural weld defects, a convolutional neural network (CNN) classification model and a ResNet50 classification model for MO images of natural weld defects are established, and the model parameters are evaluated and optimized. The experimental results show that the overall classification accuracy of the ResNet50 model is 99%. Compared with the PCA-SVM model and CNN model, the overall classification accuracy was increased by 7.4% and 1.8%, and the classification accuracy of gas pore increased by 10% and 4%, respectively, indicating that the ResNet50 model can effectively and accurately classify natural weld defects.

This study investigates the magneto-optical imaging (MOI) characteristics of weld defects under alternating magnetic field excitation. A magneto-optical sensor is employed to detect different types of weld defects, and the correlation between MOI features and magnetic field intensity is analyzed based on the Faraday magneto-optical effect. A finite element analysis (FEA) model integrated with a magnetic dipole model is established to explore the relationship between lift-off values and leakage magnetic field intensity, while clarifying the connection between magnetic flux leakage (MFL) signals and defect size as well as type. The results demonstrate that defects of varying sizes and types generate distinct MFL intensities. Meanwhile, in the MOI-based nondestructive testing (NDT) experiments, the gray values of MO images corresponding to defects of different sizes and types exhibit significant differences, indicating that the gray values of MO images can reflect the magnitude of leakage magnetic field defects. This research lays a theoretical foundation for industrial MOI nondestructive testing and provides clear engineering guidance for defect detection.