Search Results (36)

External lighting is essential for autonomous inspections of concrete structures in low-light environments. However, previous studies have primarily relied on uniformly diffused lighting to illuminate images and faced challenges in detecting complex crack patterns. This paper proposes two novel algorithms that use directional lighting to classify concrete defects. The first method, named fused neural network, uses the maximum intensity pixel-level image fusion technique and selects the maximum intensity pixel values from all directional images for each pixel to generate a fused image. The second proposed method, named multi-channel neural network, generates a five-channel image, with each channel representing the grayscale version of images captured in the Right (R), Down (D), Left (L), Up (U), and Diffused (A) directions, respectively. The proposed multi-channel neural network model achieved the best performance, with accuracy, precision, recall, and F1 score of 96.6%, 96.3%, 97%, and 96.6%, respectively. It also outperformed the FusedNet and other models found in the literature, with no significant change in evaluation time. The results from this work have the potential to improve concrete crack classification in environments where external illumination is required. Future research focuses on extending the concepts of multi-channel and image fusion to white-box techniques. Full article

To address the challenges of manual inspection dependency, low efficiency, and high costs in evaluating the surface grinding quality of composite materials, this study investigated machine vision-based surface recognition algorithms. We proposed a multi-scale texture fusion analysis algorithm that innovatively integrated luminance analysis with multi-scale texture features through decision-level fusion. Specifically, a modified Rayleigh parameter was developed during luminance analysis to rapidly pre-segment unpolished areas by characterizing surface reflection properties. Furthermore, we enhanced the traditional Otsu algorithm by incorporating global grayscale mean (μ) and standard deviation (σ), overcoming its inherent limitations of exclusive reliance on grayscale histograms and lack of multimodal feature integration. This optimization enables simultaneous detection of specular reflection defects and texture uniformity variations. To improve detection window adaptability across heterogeneous surface regions, we designed a multi-scale texture analysis framework operating at multiple resolutions. Through decision-level fusion of luminance analysis and multi-scale texture evaluation, the proposed algorithm achieved 96% recognition accuracy with >95% reliability, demonstrating robust performance for automated surface grinding quality assessment of composite materials. Full article

In underwater signal processing, accurate time delay estimation (TDE) is of crucial importance for ensuring the reliability of data transmission. However, the complex propagation of sound waves and strong noise interference in the underwater environment make this task extremely challenging. Especially under the condition of low signal-to-noise ratio (SNR), the existing methods based on cross-correlation and deep learning struggle to meet requirements. Aiming at this core issue, this paper proposed an innovative solution. Firstly, a multi-sub-window reconstruction is performed on the frequency-sliding generalized colorboxpinkcross-correlation (FS-GCC) matrix between signals to capture the time delay characteristics from different frequency bands and conduct the enhancement and extraction of features. Then, the grayscale image corresponding to the generated FS-GCC matrix is used, and the multi-level noise features are extracted by the multi-layer convolution of denoising convolutional neural network (DnCNN), effectively suppressing the noise and improving the estimation accuracy. Finally, the model-agnostic meta-learning (MAML) framework is introduced. Through training tasks under various SNR conditions, the model is enabled to possess the ability to quickly adapt to new environments, and it can achieve the desired estimation accuracy even when the number of underwater training samples is limited. Simulation validation was conducted under the NOF and NCS underwater acoustic channels, and results demonstrate that our proposed approach exhibits lower estimation errors and greater stability compared with existing methods under the same conditions. This method enhances the practicality and robustness of the model in complex underwater environments, providing strong support for the efficient and stable operation of underwater sensor networks. Full article

To address the issues of manual inspection and low precision in the detection and recognition of defects in existing animal leather, this study first establishes a leather image dataset and applies an improved Gabor filtering algorithm for image preprocessing. Specifically, the weighted average method is adopted to grayscale the image, and the algorithm parameters are designed and improved to ensure that most of the key texture information of the leather images is obtained, meeting the requirements for texture feature information in subsequent feature extraction. Next, it explores statistical feature extraction algorithms based on the gray-level co-occurrence matrix and the statistical feature extraction algorithm based on gray-level distribution, forming a combination of features for the dataset. The leather defects mainly include warble fly holes, neck wrinkles, and scars. In the processing process, there are also defects such as scratches, holes, and stains. Finally, a leather defect image classification model is proposed based on a multilayer perceptron algorithm, using the ReLU activation function and a SoftMax classifier to classify surface defects in 1280 samples. The classification time is 0.0854 s, and the average precision, recall, and accuracy for leather defect image classification are all 99.53%. This solution innovatively integrates the improved Gabor filtering with the adaptive multilayer perceptron architecture to construct a multi-modal leather defect classification model, which significantly improves the detection accuracy of three types of defects, namely holes, scratches, and stains. It provides a theoretical reference for the automation of the leather processing process. Full article

Visual odometry (VO), including keypoint detection, correspondence establishment, and pose estimation, is a crucial technique for determining motion in machine vision, with significant applications in augmented reality (AR), autonomous driving, and visual simultaneous localization and mapping (SLAM). For feature-based VO, the repeatability of keypoints affects the pose estimation. The convolutional neural network (CNN)-based detectors extract high-level features from images, thereby exhibiting robustness to viewpoint and illumination changes. Compared with descriptor matching, optical flow tracking exhibits better real-time performance. However, mainstream CNN-based detectors rely on the “joint detection and descriptor” framework to realize matching, making them incompatible with optical flow tracking. To obtain keypoints suitable for optical flow tracking, we propose a self-supervised detector based on transfer learning named OFPoint, which jointly calculates pixel-level positions and confidences. We use the descriptor-based detector simple learned keypoints (SiLK) as the pre-trained model and fine-tune it to avoid training from scratch. To achieve multi-scale feature fusion in detection, we integrate the multi-scale attention mechanism. Furthermore, we introduce the maximum discriminative probability loss term, ensuring the grayscale consistency and local stability of keypoints. OFPoint achieves a balance between accuracy and real-time performance when establishing correspondences on HPatches. Additionally, we demonstrate its effectiveness in VO and its potential for graphics applications such as AR. Full article

Image encryption is crucial for ensuring the confidentiality and integrity of digital images, preventing unauthorized access and alterations. However, existing encryption algorithms often involve complex mathematical operations or require specialized hardware, which limits their efficiency and practicality. To address these challenges, we propose a novel image encryption scheme based on the emulation of fundamental quantum operators from a multi-braided quantum group in the sense of Durdevich. These operators—coproduct, product, and braiding—are derived from quantum differential geometry and enable the dynamic generation of encryption values, avoiding the need for computationally intensive processes. Unlike quantum encryption methods that rely on physical quantum hardware, our approach simulates quantum behavior through classical computation, enhancing accessibility and efficiency. The proposed method is applied to grayscale images with 8-, 10-, and 12-bit depth per pixel. To validate its effectiveness, we conducted extensive experiments, including visual quality metrics (PSNR, SSIM), randomness evaluation using NIST 800-22, entropy and correlation analysis, key sensitivity tests, and execution time measurements. Additionally, comparative tests against AES encryption demonstrate the advantages of our approach in terms of performance and security. The results show that the proposed method provides a high level of security while maintaining computational efficiency. Full article

In this paper, we extend the definition of tensor products from using an invertible matrix to utilising right-invertible matrices, exploring the algebraic properties of these new tensor products. Based on this novel definition, we define the concepts of tensor rank and tensor nuclear norm, ensuring consistency with their matrix counterparts, and derive a singular value thresholding (${\ast }_{L,R}$ SVT) formula to approximately solve the subproblems in the alternating direction method of multipliers (ADMM), which is integral to our proposed tensor robust principal component analysis (${\ast }_{LR}$ TRPCA) algorithm. The computational complexity of the ${\ast }_{LR}$ TRPCA algorithm is $O(k·(n_1{n}_2{n}_3+p·\min (n_1^2{n}_2,n_1{n}_2^2)))$ for k iterations. According to this complexity analysis, by using a right-invertible matrix that selects p rows from the $n_3$ rows of the invertible matrix used in the tensor product with an invertible matrix, the computational load is approximately reduced to $p/n_3$ of what it would be with an invertible matrix, highlighting the efficiency gain in terms of computational resources. We apply this efficient algorithm to grayscale video denoising and motion detection problems, where it demonstrates significant improvements in processing speed while maintaining comparable quality levels to existing methods, thereby providing a promising approach for handling multi-linear data and offering valuable insights for advanced data analysis tasks. Full article

Arbitrarily designed flat optics directly manipulate the light wavefront to reproduce complex optical functions, enabling more compact optical assemblies and microsystem integration. Phase-shifting micro-optical devices rely on locally tailoring the optical path length of the wavefront through binary or multilevel surface relief micro- and nanostructures. Considering the resolution and tolerances of the production processes and the optical properties of the substrate and coating materials is crucial for designing robust multilevel diffractive flat optics. In this work, we evaluate the impact of the grayscale laser lithography resolution and geometry constraints on the efficiency of surface-relief diffractive lenses, and we analyze the process parameter space that limit lens performance. We introduce a spectral bandwidth metric to help evaluate the broad-spectrum performance of different materials. We simulate and experimentally observe that the diffractive focusing is dominated by the periodic wavelength-dependent phase discontinuities arising in the profile transitions of multilevel diffractive lenses. Full article

Transfer learning techniques for structural health monitoring in bridge-type structures are investigated, focusing on model generalizability and domain adaptation challenges. Finite element models of bridge-type structures with varying geometry were simulated using the OpenSeesPy platform. Different levels of damage states were introduced at the midspans of these models, and Gaussian-based load time histories were applied at mid-span for dynamic time-history analysis to calculate acceleration data. Then, this acceleration time-history series was transformed into grayscale images, serving as inputs for a Convolutional Neural Network developed to detect and classify structural damage states. Initially, it was trained and tested on datasets derived from a Single-Source Domain structure, achieving perfect accuracy (1.0) in a ten-label multi-class classification task. However, this accuracy significantly decreased when the model was sequentially tested on structures with different geometry without retraining. To address this challenge, it is proposed that transfer learning be employed via feature extraction and joint training. The model showed a reduction in accuracy percentage when adapting from a Single-Source Domain to Multiple-Target Domains, revealing potential issues with non-homogeneous data distribution and catastrophic forgetting. Conversely, joint training, which involves training on all datasets except the specific Target Domain, generated a generalized network that effectively mitigated these issues and maintained high accuracy in predicting unseen class labels. This study highlights the integration of simulation data into the Deep Learning-based SHM framework, demonstrating that a generalized model created via Joint Learning utilizing FEM can potentially reduce the consequences of modeling errors and operational uncertainties unavoidable in real-world applications. Full article

In visual Simultaneous Localization and Mapping (SLAM), operational efficiency and localization accuracy are equally crucial evaluation metrics. We propose an enhanced visual SLAM method to ensure stable localization accuracy while improving system efficiency. It can maintain localization accuracy even after reducing the number of feature pyramid levels by 50%. Firstly, we innovatively incorporate the principal direction error, which represents the global geometric features of feature points, into the error function for pose estimation, utilizing Pareto optimal solutions to improve the localization accuracy. Secondly, for loop-closure detection, we construct a feature matrix by integrating the grayscale and gradient direction of an image. This matrix is then dimensionally reduced through aggregation, and a multi-layer detection approach is employed to ensure both efficiency and accuracy. Finally, we optimize the feature extraction levels and integrate our method into the visual system to speed up the extraction process and mitigate the impact of the reduced levels. We comprehensively evaluate the proposed method on local and public datasets. Experiments show that the SLAM method maintained high localization accuracy after reducing the tracking time by 24% compared with ORB SLAM3. Additionally, the proposed loop-closure-detection method demonstrated superior computational efficiency and detection accuracy compared to the existing methods. Full article

Semantic segmentation is crucial for a wide range of downstream applications in remote sensing, aiming to classify pixels in remote sensing images (RSIs) at the semantic level. The dramatic variations in grayscale and the stacking of categories within RSIs lead to unstable inter-class variance and exacerbate the uncertainty around category boundaries. However, existing methods typically emphasize spatial information while overlooking frequency insights, making it difficult to achieve desirable results. To address these challenges, we propose a novel dual-domain fusion network that integrates both spatial and frequency features. For grayscale variations, a multi-level wavelet frequency decomposition module (MWFD) is introduced to extract and integrate multi-level frequency features to enhance the distinctiveness between spatially similar categories. To mitigate the uncertainty of boundaries, a type-2 fuzzy spatial constraint module (T2FSC) is proposed to achieve flexible higher-order fuzzy modeling to adaptively constrain the boundary features in the spatial by constructing upper and lower membership functions. Furthermore, a dual-domain feature fusion (DFF) module bridges the semantic gap between the frequency and spatial features, effectively realizes semantic alignment and feature fusion between the dual domains, which further improves the accuracy of segmentation results. We conduct comprehensive experiments and extensive ablation studies on three well-known datasets: Vaihingen, Potsdam, and GID. In these three datasets, our method achieved 74.56%, 73.60%, and 81.01% mIoU, respectively. Quantitative and qualitative results demonstrate that the proposed method significantly outperforms state-of-the-art methods, achieving an excellent balance between segmentation accuracy and computational overhead. Full article

Multi-modal image fusion is a methodology that combines image features from multiple types of sensors, effectively improving the quality and content of fused images. However, most existing deep learning fusion methods need to integrate global or local features, restricting the representation of feature information. To address this issue, a hybrid densely connected CNN and transformer (HDCCT) fusion framework is proposed. In the proposed HDCCT framework, the network of the CNN-based blocks obtain the local structure of the input data, and the transformer-based blocks obtain the global structure of the original data, significantly improving the feature representation. In the fused image, the proposed encoder–decoder architecture is designed for both the CNN and transformer blocks to reduce feature loss while preserving the characterization of all-level features. In addition, the cross-coupled framework facilitates the flow of feature structures, retains the uniqueness of information, and makes the transform model long-range dependencies based on the local features already extracted by the CNN. Meanwhile, to retain the information in the source images, the hybrid structural similarity (SSIM) and mean square error (MSE) loss functions are introduced. The qualitative and quantitative comparisons of grayscale images with infrared and visible image fusion indicate that the suggested method outperforms related works. Full article

Underwater images, as a crucial medium for storing ocean information in underwater sensors, play a vital role in various underwater tasks. However, they are prone to distortion due to the imaging environment, which leads to a decline in visual quality, which is an urgent issue for various marine vision systems to address. Therefore, it is necessary to develop underwater image enhancement (UIE) and corresponding quality assessment methods. At present, most underwater image quality assessment (UIQA) methods primarily rely on extracting handcrafted features that characterize degradation attributes, which struggle to measure complex mixed distortions and often exhibit discrepancies with human visual perception in practical applications. Furthermore, current UIQA methods lack the consideration of the perception perspective of enhanced effects. To this end, this paper employs luminance and saliency priors as critical visual information for the first time to measure the enhancement effect of global and local quality achieved by the UIE algorithms, named JLSAU. The proposed JLSAU is built upon an overall pyramid-structured backbone, supplemented by the Luminance Feature Extraction Module (LFEM) and Saliency Weight Learning Module (SWLM), which aim at obtaining perception features with luminance and saliency priors at multiple scales. The supplement of luminance priors aims to perceive visually sensitive global distortion of luminance, including histogram statistical features and grayscale features with positional information. The supplement of saliency priors aims to perceive visual information that reflects local quality variation both in spatial and channel domains. Finally, to effectively model the relationship among different levels of visual information contained in the multi-scale features, the Attention Feature Fusion Module (AFFM) is proposed. Experimental results on the public UIQE and UWIQA datasets demonstrate that the proposed JLSAU outperforms existing state-of-the-art UIQA methods. Full article

Grayscale lithography (GSL) is an alternative approach to the standard binary lithography in MEMS fabrication, enabling the fabrication of complicated, arbitrary 3D structures on a wafer without the need for multiple masks and exposure steps. Despite its advantages, GSL’s effectiveness is highly dependent on controlled lab conditions, equipment consistency, and finely tuned photoresist (PR) exposure and etching processes. This works presents a thorough investigation of the challenges of GSL for silicon (Si) wafers and presents a detailed approach on how to minimize fabrication inaccuracies, aiming to replicate the intended design as closely as possible. Utilizing a maskless laser writer, all aspects of the GSL are analyzed, from photoresist exposure parameters to Si etching conditions. A practical application of GSL is demonstrated in the fabrication of 4-μm-deep $f$#/1 Si Fresnel lenses for long-wave infrared (LWIR) imaging (8–12 μm). The surface topography of a Fresnel lens is a good case to apply GSL, as it has varying shapes and size features that need to be preserved. The final fabricated lens profiles show a good match with the initial design, and demonstrate successful etching of coarse and fine features, and demonstrative images taken with an LWIR camera. Full article

The accurate assessment of peanut seed plumpness is crucial for optimizing peanut production and quality. The current method is mainly manual and visual inspection, which is very time-consuming and causes seed deterioration. A novel imaging technique is used to enhance the detection of peanut seed fullness using a non-destructive soft X-ray, which is suitable for the analysis of the surface or a thin layer of a material. The overall grayscale of the peanut is similar to the background, and the edge of the peanut seed is blurred. The inaccuracy of peanut overall and peanut seed segmentation leads to low accuracy of seed plumpness detection. To improve accuracy in detecting the fullness of peanut seeds, a seed plumpness detection method based on level set and multi-threshold segmentation was proposed for peanut images. Firstly, the level set algorithm is used to extract the overall contour of peanuts. Secondly, the obtained binary image is processed by morphology to obtain the peanut pods (the peanut overall). Then, the multi-threshold OTSU algorithm is used for threshold segmentation. The threshold is selected to extract the peanut seed part. Finally, morphology is used to complete the cavity to achieve the segmentation of the peanut seed. Compared with optimization algorithms, in the segmentation of the peanut pods, average random index (RI), global consistency error (GCE) and variation of information (VI) were increased by 10.12% and decreased by 0.53% and 24.11%, respectively. Compared with existing algorithms, in the segmentation of the peanut seed, the average RI, VI and GCE were increased by 18.32% and decreased by 9.14% and 6.11%, respectively. The proposed method is stable, accurate and can meet the requirements of peanut image plumpness detection. It provides a feasible technical means and reference for scientific experimental breeding and testing grading service pricing. Full article