Search Results (221)

Objective: The accurate visualization of root canal systems on periapical radiographs is critical for successful endodontic treatment. This study aimed to evaluate and compare the effectiveness of several image enhancement algorithms—including a novel Total Variation–Contrast-Limited Adaptive Histogram Equalization (TV-CLAHE) technique—in improving the detectability of root canal configurations in mandibular incisors, using cone-beam computed tomography (CBCT) as the gold standard. A null hypothesis was tested, assuming that enhancement methods would not significantly improve root canal detection compared to original radiographs. Method: A retrospective analysis was conducted on 60 periapical radiographs of mandibular incisors, resulting in 420 images after applying seven enhancement techniques: Histogram Equalization (HE), Contrast-Limited Adaptive Histogram Equalization (CLAHE), CLAHE optimized with Pelican Optimization Algorithm (CLAHE-POA), Global CLAHE (G-CLAHE), k-Caputo Fractional Differential Operator (KCFDO), and the proposed TV-CLAHE. Four experienced observers (two radiologists and two dentists) independently assessed root canal visibility. Subjective evaluation was performed using an own scale inspired by a 5-point Likert scale, and the detection accuracy was compared to the CBCT findings. Quantitative metrics including Peak Signal-to-Noise Ratio (PSNR), Signal-to-Noise Ratio (SNR), image entropy, and Structural Similarity Index Measure (SSIM) were calculated to objectively assess image quality. Results: Root canal detection accuracy improved across all enhancement methods, with the proposed TV-CLAHE algorithm achieving the highest performance (93–98% accuracy), closely approaching CBCT-level visualization. G-CLAHE also showed substantial improvement (up to 92%). Statistical analysis confirmed significant inter-method differences (p < 0.001). TV-CLAHE outperformed all other techniques in subjective quality ratings and yielded superior SNR and entropy values. Conclusions: Advanced image enhancement methods, particularly TV-CLAHE, significantly improve root canal visibility in 2D radiographs and offer a practical, low-cost alternative to CBCT in routine dental diagnostics. These findings support the integration of optimized contrast enhancement techniques into endodontic imaging workflows to reduce the risk of missed canals and improve treatment outcomes. Full article

Engineering innovations play a critical role in achieving the United Nations’ Sustainable Development Goals, especially in human–robotic interaction and precise engineering. For the robot, writing Chinese calligraphy with hairy brush pen is a form of precision operation. Existing writing trajectory control models mainly focus on writing trajectory models, and the fine-grained trajectory control model based on brush strokes is not studied. The problem of how to establish writing trajectory control based on brush stroke model needs to be solved. On the basis of the proposed composite-curve-dilation brush stroke model (CCD-BSM), this study investigates the control methods of intelligent calligraphy robots and proposed fine-grained writing trajectory control models that conform to the rules of brush calligraphy to reflect the local writing characteristics. By decomposing and refining each writing process, control models in the process of brush movement are analyzed and modeled. According to the writing rules, fine-grained writing trajectory control models of strokes are established based on the CCD-BSM. The parametric representations of the control models are built for the three stages of initiation, execution, and completion of strokes writing. Experimental results demonstrate that the proposed fine-grained control models can exhibit excellent performances in basic strokes and Chinese characters with better writing capabilities. Compared with existing models, the writing results demonstrate the advantages of our proposed model in terms of high average similarity with two quantitative indicators Cosine similarity (CSIM) and Structural similarity index measure (SSIM), which are 99.54% and 97.57%, respectively. Full article

Deep learning-based super-resolution (SR) frameworks are widely used in remote sensing applications. However, existing SR models still face limitations, particularly in recovering contours, fine features, and textures, as well as in effectively integrating channel information. To address these challenges, this study introduces a novel residual model named OARN (Optimized Attention Residual Network) specifically designed to enhance the visual quality of low-resolution images. The network operates on the Y channel of the YCbCr color space and integrates LKA (Large Kernel Attention) and OCM (Optimized Convolutional Module) blocks. These components can restore large-scale spatial relationships and refine textures and contours, improving feature reconstruction without significantly increasing computational complexity. The performance of OARN was evaluated using satellite images from WorldView-2, GaoFen-2, and Microsoft Virtual Earth. Evaluation was conducted using objective quality metrics, such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Edge Preservation Index (EPI), and Perceptual Image Patch Similarity (LPIPS), demonstrating superior results compared to state-of-the-art methods in both objective measurements and subjective visual perception. Moreover, OARN achieves this performance while maintaining computational efficiency, offering a balanced trade-off between processing time and reconstruction quality. Full article

Traditional Foreign Object Debris (FOD) detection methods face challenges such as difficulties in large-size data acquisition and the ineffective application of detection algorithms with high accuracy. In this paper, image data augmentation was performed using generative adversarial networks and diffusion models, generating images of monitoring areas under different environmental conditions and FOD images of varied types. Additionally, a three-stage image blending method considering size transformation, a seamless process, and style transfer was proposed. The image quality of different blending methods was quantitatively evaluated using metrics such as structural similarity index and peak signal-to-noise ratio, as well as Depthanything. Finally, object detection models with a similarity distance strategy (SimD), including Faster R-CNN, YOLOv8, and YOLOv11, were tested on the dataset. The experimental results demonstrated that realistic FOD data were effectively generated. The Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR) of the synthesized image by the proposed three-stage image blending method outperformed the other methods, reaching 0.99 and 45 dB. YOLOv11 with SimD trained on the augmented dataset achieved the mAP of 86.95%. Based on the results, it could be concluded that both data augmentation and SimD significantly improved the accuracy of FOD detection. Full article

Automotive intelligent agents are increasingly collecting facial data for applications such as driver behavior monitoring and identity verification. These excessive collections of facial data bring serious risks of sensitive information leakage to autonomous driving. Facial information has been explicitly required to be anonymized, but the availability of most desensitized facial data is poor, which will greatly affect its application in autonomous driving. This paper proposes an automotive sensitive information anonymization method with high-quality generated facial images by considering the data availability under privacy protection. By comparing K-Same and Generative Adversarial Networks (GANs), this paper proposes a hierarchical self-attention mechanism in StyleGAN3 to enhance the feature perception of face images. The synchronous regularization of sample data is applied to optimize the loss function of the discriminator of StyleGAN3, thereby improving the convergence stability of the model. The experimental results demonstrate that the proposed facial desensitization model reduces the Frechet inception distance (FID) and structural similarity index measure (SSIM) by 95.8% and 24.3%, respectively. The image quality and privacy desensitization of the facial data generated by the StyleGAN3 model have been fully verified in this work. This research provides an efficient and robust facial privacy protection solution for autonomous driving, which is conducive to promoting the security guarantee of automotive data. Full article

Efficient prediction of shallow-water acoustic transmission loss (TL) is crucial for underwater detection, recognition, and communication systems. Traditional physical modeling methods require repeated calculations for each new scenario in practical waveguide environments, leading to low computational efficiency. Deep learning approaches, based on data-driven principles, enable accurate input–output approximation and batch processing of large-scale datasets, significantly reducing computation time and cost. To establish a rapid prediction model mapping sound speed profiles (SSPs) to acoustic TL through controllable generation, this study proposes a hybrid framework that integrates a variational autoencoder (VAE) and a normalizing flow (Flow) through a two-stage training strategy. The VAE network is employed to learn latent representations of TL data on a low-dimensional manifold, while the Flow network is additionally used to establish a bijective mapping between the latent variables and underwater physical parameters, thereby enhancing the controllability of the generation process. Combining the trained normalizing flow with the VAE decoder could establish an end-to-end mapping from SSPs to TL. The results demonstrated that the VAE–Flow network achieved higher computational efficiency, with a computation time of 4 s for generating 1000 acoustic TL samples, versus the over 500 s required by the KRAKEN model, while preserving accuracy, with median structural similarity index measure (SSIM) values over 0.90. Full article

Defect detection in mass production lines often involves small and imbalanced datasets, necessitating the use of few-shot learning methods. Traditional deep learning-based approaches typically rely on large datasets, limiting their applicability in real-world scenarios. This study explores few-shot learning models for detecting product defects using limited data, enhancing model generalization and stability. Unlike previous deep learning models that require extensive datasets, our approach effectively performs defect detection with minimal data. We propose a Siamese network that integrates Residual blocks, Squeeze and Excitation blocks, and Convolution Block Attention Modules (ResNet-SE-CBAM Siamese network) for feature extraction, optimized through triplet loss for embedding learning. The ResNet-SE-CBAM Siamese network incorporates two primary features: attention mechanisms and metric learning. The recently developed attention mechanisms enhance the convolutional neural network operations and significantly improve feature extraction performance. Meanwhile, metric learning allows for the addition or removal of feature classes without the need to retrain the model, improving its applicability in industrial production lines with limited defect samples. To further improve training efficiency with imbalanced datasets, we introduce a sample selection method based on the Structural Similarity Index Measure (SSIM). Additionally, a high defect rate training strategy is utilized to reduce the False Negative Rate (FNR) and ensure no missed defect detections. At the classification stage, a K-Nearest Neighbor (KNN) classifier is employed to mitigate overfitting risks and enhance stability in few-shot conditions. The experimental results demonstrate that with a good-to-defect ratio of 20:40, the proposed system achieves a classification accuracy of 94% and an FNR of 2%. Furthermore, when the number of defective samples increases to 80, the system achieves zero false negatives (FNR = 0%). The proposed metric learning approach outperforms traditional deep learning models, such as parametric-based YOLO series models in defect detection, achieving higher accuracy and lower miss rates, highlighting its potential for high-reliability industrial deployment. Full article

To further enhance the stability and security of image transmission in FSO (Free Space Optics) aviation platforms, this paper proposes a communication transmission scheme that integrates a chaotic image encryption system with the HAP (high-altitude platform) environment. This scheme effectively combines the chaotic image encryption algorithm with the atmospheric turbulence channel transmission process, improving the anti-interference capabilities and security of HAP optical communication for image transmission. First, a five-dimensional hyperchaotic system with complex dynamic characteristics is introduced, and the system’s chaotic behaviors and dynamic properties are explored. The improved system model incorporates chaotic mapping and DNA coding techniques, forming a robust chaotic image encryption system, whose performance is experimentally validated. Next, the feasibility of integrating the chaotic image encryption system with HAP optical communication is discussed. A detailed description of the corresponding turbulence model and test conditions is provided. To verify the scheme’s feasibility, plaintext images of varying sizes are selected for experiments, comparing the transmission performance of both unencrypted and encrypted images under three turbulence levels: weak, medium, and strong. The impact on image communication quality is quantitatively analyzed using PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index measure). Finally, the effect of malicious interception attacks, caused by noise interference from different levels of atmospheric turbulence, is examined. The robustness and feasibility of the proposed scheme are validated, providing a promising approach for integrating HAP optical communication’s anti-turbulence capabilities with chaotic image encryption. Full article

The reconstruction of high-resolution (HR) remote sensing images (RSIs) from low-resolution (LR) counterparts is a critical task in remote sensing image super-resolution (RSISR). Recent advancements in convolutional neural networks (CNNs) and Transformers have significantly improved RSISR performance due to their capabilities in local feature extraction and global modeling. However, several limitations remain, including the underutilization of multi-scale features in RSIs, the limited receptive field of Swin Transformer’s window self-attention (WSA), and the computational complexity of existing methods. To address these issues, this paper introduces the NGSTGAN model, which employs an N-Gram Swin Transformer as the generator and a multi-attention U-Net as the discriminator. The discriminator enhances attention to multi-scale key features through the addition of channel, spatial, and pixel attention (CSPA) modules, while the generator utilizes an improved shallow feature extraction (ISFE) module to extract multi-scale and multi-directional features, enhancing the capture of complex textures and details. The N-Gram concept is introduced to expand the receptive field of Swin Transformer, and sliding window self-attention (S-WSA) is employed to facilitate interaction between neighboring windows. Additionally, channel-reducing group convolution (CRGC) is used to reduce the number of parameters and computational complexity. A cross-sensor multispectral dataset combining Landsat-8 (L8) and Sentinel-2 (S2) is constructed for the resolution enhancement of L8’s blue (B), green (G), red (R), and near-infrared (NIR) bands from 30 m to 10 m. Experiments show that NGSTGAN outperforms the state-of-the-art (SOTA) method, achieving improvements of 0.5180 dB in the peak signal-to-noise ratio (PSNR) and 0.0153 in the structural similarity index measure (SSIM) over the second best method, offering a more effective solution to the task. Full article

The precise identification and non-destructive measurement of structural features and defects in semiconductor wafers are essential for ensuring process integrity and sustaining high yield in advanced manufacturing environments. Unlike conventional measurement techniques, scanning acoustic microscopy (SAM) is an advanced method that provides detailed visualizations of both surface and internal wafer structures. However, in practical industrial applications, the scanning time and image quality of SAM significantly impact its overall performance and utility. Prolonged scanning durations can lead to production bottlenecks, while suboptimal image quality can compromise the accuracy of defect detection. To address these challenges, this study proposes LinearTGAN, an improved generative adversarial network (GAN)-based model specifically designed to improve the resolution of linear acoustic wafer images acquired by the breakthrough rotary scanning acoustic microscopy (R-SAM) system. Empirical evaluations demonstrate that the proposed model significantly outperforms conventional GAN-based approaches, achieving a Peak Signal-to-Noise Ratio (PSNR) of 29.479 dB, a Structural Similarity Index Measure (SSIM) of 0.874, a Learned Perceptual Image Patch Similarity (LPIPS) of 0.095, and a Fréchet Inception Distance (FID) of 0.445. To assess the measurement aspect of LinearTGAN, a lightweight defect segmentation module was integrated and tested on annotated wafer datasets. The super-resolved images produced by LinearTGAN significantly enhanced segmentation accuracy and improved the sensitivity of microcrack detection. Furthermore, the deployment of LinearTGAN within the R-SAM system yielded a 92% improvement in scanning performance for 12-inch wafers while simultaneously enhancing image fidelity. The integration of super-resolution techniques into R-SAM significantly advances the precision, robustness, and efficiency of non-destructive measurements, highlighting their potential to have a transformative impact in semiconductor metrology and quality assurance. Full article

This paper presents a new high-speed RGB image transmission system over Free-Space Optics (FSO) channel employing Optical Code Division Multiple Access (OCDMA) with Permutation Vector (PV) codes. Four RGB images are transmitted simultaneously at 10 Gbps per image, achieving a total capacity of 40 Gbps. The system’s performance is evaluated under various atmospheric conditions, including three fog levels and real-world visibility data from Alexandria city, Egypt. Image Quality Assessment (IQA) metrics, including Signal-to-Noise Ratio (SNR), Root Mean Square Error (RMSE), Peak Signal-to-Noise Ratio (PSNR), correlation coefficients, and Structural Similarity Index Measure (SSIM), are evaluated for both unfiltered and median-filtered images. The results show significant degradation in image quality due to transmission distance and atmospheric attenuation. In Alexandria’s clear atmospheric conditions, the system achieves a maximum transmission range of 15 km with acceptable visual quality, while the range is reduced to 2.6 km, 1.6 km, and 1 km for Low Fog (LF), Medium Fog (MF), and Heavy Fog (HF), respectively. At these distances, the RGB images achieve minimum SNR, RMSE, and SSIM values of 7.27 dB, 47.66, and 0.20, respectively, with further improvements when applying median filtering. Full article

The electrically evoked compound action potential (ECAP) is a crucial physiological signal used by clinicians to evaluate auditory nerve functionality. Clean ECAP recordings help to accurately estimate auditory neural activity patterns and ECAP magnitudes, particularly through the panoramic ECAP (PECAP) framework. However, noise—especially in low-signal-to-noise ratio (SNR) conditions—can lead to significant errors in parameter estimation. This study proposes a two-stage preprocessing denoising (TSPD) algorithm to address this issue and enhance ECAP signals. First, an ECAP matrix is constructed using the forward-masking technique, representing the signal as a two-dimensional image. This matrix undergoes spatial noise reduction via an improved spatial median (I-Median) filter. In the second stage, the denoised matrix is vectorized and further processed using a log-spectral amplitude (LSA) Wiener filter for spectral domain denoising. The enhanced vector is then reconstructed into the ECAP matrix for parameter estimation using PECAP. The above integrated spatial-spectral denoising framework is denoted as PECAP-TSPD in this work. Evaluations are conducted using a simulation-based ECAP model mixed with simulated and experimental noise, designed to emulate the spatial characteristics of real ECAPs. Three objective quality measures—namely, normalized root mean square error (RMSE), two-dimensional correlation coefficient (TDCC), and structural similarity index (SSIM)—are used. Simulated and experimental results show that the proposed PECAP-TSPD method has the lowest average RMSE of PECAP magnitudes (1.952%) and auditory neural patterns (1.407%), highest average TDCC (0.9988), and average SSIM (0.9931) compared to PECAP (6.446%, 5.703%, 0.9859, 0.8997), PECAP with convolutional neural network (CNN)-based denoising mask (PECAP-CNN) (9.700%, 7.111%, 0.9766, 0.8832), and PECAP with improved median filtering (PECAP-I-Median) (4.515%, 3.321%, 0.9949, 0.9470) under impulse noise conditions. Full article

The main function of triangulation-based laser profile sensors—also referred to as laser profilometers or profilers—is the three-dimensional scanning of moving objects using laser triangulation. In addition to capturing 3D data, these profilometers simultaneously generate grayscale images of the scanned objects. However, the quality of these images is often degraded due to interference of the laser light, manifesting as speckle noise. In profilometer images, this noise typically appears as vertical stripes. Unlike the column fixed pattern noise commonly observed in TDI CMOS cameras, the positions of these stripes are not stationary. Consequently, conventional algorithms for removing fixed pattern noise yield unsatisfactory results when applied to profilometer images. In this article, we propose an effective method for suppressing speckle noise in profilometer images of flat surfaces, based on local column median vectors. The method was evaluated across a variety of surface types and compared against existing approaches using several metrics, including the standard deviation of the column mean vector (SDCMV), frequency spectrum analysis, and standard image quality assessment measures. Our results demonstrate a substantial improvement in reducing column speckle noise: the SDCMV value achieved with our method is 2.5 to 5 times lower than that obtained using global column median values, and the root mean square (RMS) of the frequency spectrum in the noise-relevant region is reduced by nearly an order of magnitude. General image quality metrics also indicate moderate enhancement: peak signal-to-noise ratio (PSNR) increased by 2.12 dB, and the structural similarity index (SSIM) improved from 0.929 to 0.953. The primary limitation of the proposed method is its applicability only to flat surfaces. Nonetheless, we successfully implemented it in an optical inspection system for the furniture industry, where the post-processed image quality was sufficient to detect surface defects as small as 0.1 mm. Full article

This study investigates the noise impact on reconstructed images in computer-generated holography (CGH) through theoretical analysis and Matlab 2015b simulations. By quantitatively injecting noise to mimic practical interference environments, we systematically analyze the degradation mechanisms of four CGH types: detour-phase, modified off-axis beam reference, kinoform, and interference type. A dual-metric evaluation framework combining peak signal-to-noise ratio (PSNR) and the Structural Similarity Index Measure (SSIM) is proposed. Results demonstrate that increasing noise intensity induces progressive declines in reconstruction quality, manifested as PSNR reduction and SSIM-based structural fidelity loss. The findings provide theoretical guidance for noise suppression, parameter optimization, and algorithm selection in CGH systems, advancing its applications in optical encryption and high-precision imaging. Full article

With the rise of smart manufacturing, defect detection in small-size liquid crystal display (LCD) screens has become essential for ensuring product quality. Traditional manual inspection is inefficient and labor-intensive, making it unsuitable for modern automated production. Although machine vision techniques offer improved efficiency, the lack of high-quality defect datasets limits their performance. To overcome this, we propose a symmetry-aware generative framework, the Squeeze-and-Excitation Wasserstein GAN with Gradient Penalty and Visual Geometry Group(VGG)-based perceptual loss (SWG-VGG), for realistic defect image synthesis.By leveraging the symmetry of feature channels through attention mechanisms and perceptual consistency, the model generates high-fidelity defect images that align with real-world structural patterns. Evaluation using the You Only Look Once version 8(YOLOv8) detection model shows that the synthetic dataset improves mAP@0.5 to 0.976—an increase of 10.5% over real-data-only training. Further assessment using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Root Mean Square Error (RMSE), and Content Similarity (CS) confirms the visual and structural quality of the generated images.This symmetry-guided method provides an effective solution for defect data augmentation and aligns closely with Symmetry’s emphasis on structured pattern generation in intelligent vision systems. Full article