Search

A color rendition chart, the preferred memory color (PMC) chart, has been produced. It comprises 30 colored patches, divided into three groups: preferred memory colors, reference color‐gamut colors, and a gray scale. The main purpose of the new chart is to enable users to produce satisfactory preferred color reproduction using digital cameras, displays, and printing systems. The methods used to develop the various colors, and the color specification of each color are presented. Finally, several potential applications of the chart for the characterization of imaging devices, for the evaluation of image color quality, and for the calculation of color rendering indices for lighting are suggested. [ABSTRACT FROM AUTHOR]

The American Institute of Ultrasound in Medicine (AIUM) has developed the Practice Parameter for the Performance of Ultrasound of the Female Pelvis, which provides recommendations for high-quality ultrasound examinations in this specialty area. The document outlines indications for pelvic sonography, qualifications and responsibilities of personnel, preparation for the examination, and detailed specifications for evaluating the uterus, adnexae (ovaries and fallopian tubes), and cul-de-sac. It emphasizes the importance of accurate documentation, equipment specifications, quality assurance, safety, infection control, and adherence to the ALARA principle. The parameter was developed in collaboration with various organizations and committees, reflecting a multidisciplinary approach to advancing the safe and effective use of ultrasound in medicine. [Extracted from the article]

Context Thyrotoxicosis requires accurate and expeditious differentiation between Graves' disease (GD) and thyroiditis to ensure effective treatment decisions. Objective This study aimed to develop a machine learning algorithm using ultrasonography and Doppler images to differentiate thyrotoxicosis subtypes, with a focus on GD. Methods This study included patients who initially presented with thyrotoxicosis and underwent thyroid ultrasonography at a single tertiary hospital. A total of 7719 ultrasonography images from 351 patients with GD and 2980 images from 136 patients with thyroiditis were used. Data augmentation techniques were applied to enhance the algorithm's performance. Two deep learning models, Xception and EfficientNetB0_2, were employed. Performance metrics such as accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score were calculated for both models. Image preprocessing, neural network model generation, and neural network training results verification were performed using DEEP:PHI® platform. Results The Xception model achieved 84.94% accuracy, 89.26% sensitivity, 73.17% specificity, 90.06% PPV, 71.43% NPV, and an F1 score of 89.66 for the diagnosis of GD. The EfficientNetB0_2 model exhibited 85.31% accuracy, 90.28% sensitivity, 71.78% specificity, 89.71% PPV, 73.05% NPV, and an F1 score of 89.99. Conclusion Machine learning models based on ultrasound and Doppler images showed promising results with high accuracy and sensitivity in differentiating GD from thyroiditis. [ABSTRACT FROM AUTHOR]

Human studies often rely on wearable lifelogging cameras that capture videos of individuals and their surroundings to aid in visual confirmation or recollection of daily activities like eating, drinking, and smoking. However, this may include private or sensitive information that may cause some users to refrain from using such monitoring devices. Also, short battery lifetime and large form factors reduce applicability for long-term capture of human activity. Solving this triad of interconnected problems is challenging due to wearable embedded systems' energy, memory, and computing constraints. Inspired by this critical use case and the unique design problem, we developed NIR-sighted, an architecture for wearable video cameras that navigates this design space via three key ideas: (i) reduce storage and enhance privacy by discarding masked pixels and frames, (ii) enable programmers to generate effective masks with low computational overhead, and (iii) enable the use of small MCUs by moving masking and compression off-chip. Combined together in an end-to-end system, NIR-sighted's masking capabilities and off-chip compression hardware shrinks systems, stores less data, and enables programmer-defined obfuscation to yield privacy enhancement. The user's privacy is enhanced significantly as nowhere in the pipeline is any part of the image stored before it is obfuscated. We design a wearable camera called NIR-sightedCam based on this architecture; it is compact and can record IR and grayscale video at 16 and 20+ fps, respectively, for 26 hours nonstop (59 hours with IR disabled) at a fraction of comparable platforms power draw. NIR-sightedCam includes a low-power Field Programmable Gate Array that implements our mJPEG compress/obfuscate hardware, Blindspot. We additionally show the potential for privacy-enhancing function and clinical utility via an in-lab eating study, validated by a nutritionist. [ABSTRACT FROM AUTHOR]

In this paper, a (t, n) threshold quantum image secret sharing scheme based on combination theory is proposed. Here, the threshold t is a constant number that should satisfy the condition t ≤ n . In sharing process, the secret image is divided into n shadow images according to n sample matrices constructed by the combination theory and sent to n participants individually. During the recovery process, the original secret image can be fully restored if q (q ≥ t) participants are chosen. However, if the number of chosen participants is less than t, no information about the original secret image can be obtained. The quantum matrix multiplier is first introduced for encryption of the secret images. Then the quantum ⋂ gate is chosen for producing sample matrices. In the recovering steps, we use quantum ⋃ gates to collect shadow images. After that, the quantum circuits of the proposed scheme are given and the complexity of the circuits is discussed. We then conduct numerical simulations of our scheme on grayscale images and RGB images. The results shows that our scheme has a good effect on threshold quantum image secret sharing. [ABSTRACT FROM AUTHOR]

To extract maximum features ResAttNet (RAN) network structure is chosen as an alternative to the convolutional layer and it enhances image feature extraction. Additionally, a Deformable Convolution (DC) network was included to provide a feature extraction module, improving the model's capacity to simulate vessel deformation. Apart from the two additional networks because of inadequate quality in retinal data, before model building pre-processing is done. The data is processed by CLAHE, normalization, grayscale transformation, and gamma transformation. Second, the fundamental network structure model U-net is constructed, and the ResAttNet (RAN) structure and DC network are combined to form the ARDC-UNet network. Experimental data, both quantitative and qualitative, demonstrate the efficiency and accuracy with which our ARDC-UNet can segment retinal vessels. [ABSTRACT FROM AUTHOR]

Image steganography is an extremely rich and significant exploration region that gives productive answers to some genuine and modern issues. This paper deals with secret image transmission and securing it from different attacks. The proposed image steganography technique uses a combination of image segmentation, pre-processing, and scrambling methos. The proposed technique begins with the segmentation of secret and cover images using Rubik's cube. The segmentation process breaks the images into six parts, then after they are stored in a segmented image dataset. In the second step, each segmented secret image is processed by the image pre-processing method. The proposed image pre-processing method helps the system select the appropriate cover image from the segmented cover image dataset, which makes the technique more robust. In the third step, before the embedding process, secret images are scrambled using the proposed scrambling method. Finally, the cover and secret images are processed by discrete wavelet transforms (DWT) and singular value decomposition (SVD) to generate the stego image. The proposed technique is tested on a variety of grayscale images, with peak signal-to-noise ratio (PSNR) values ranging from 32.27 to 30.77 (dB) and structural similarity index measure (SSIM) values ranging from 0.93 to 0.90 for different alpha values. The extracted secret image is analyzed using normalized correlation (NC) and naturalness image quality evaluator (NIQE) parameters. The NC values are above 0.99, and the NIQE values ranged from 3.3264 to 3.8468 for various extracted images. To analyze the proposed technique, measured value of entropy and an elapse time are 7.7956 and 6.489 s, respectively. Comparative studies are conducted in four main areas. The first comparative study tested the reliability of the proposed scrambling method by calculating the overall and diagonal correlation values of the secret image and scrambled secret image. The second comparative study tested the impeccability and reliability of the stego image by comparing its PSNR value to other stego images produced by other researchers. The third comparative study tested the effect of false-positive tests on extracted secret images. The results showed that the extracted secret image could only be obtained from the original stego image, indicating that the proposed method was secure against false positives. The fourth or last comparative study compares the computational load of proposed technique with previously developed techniques. In general, the results of the comparative study show that the proposed technique is reliable and secure for image scrambling, stego image generation, and secret image extraction. [ABSTRACT FROM AUTHOR]

Recent developments indicate that malware programs present a significant risk in the security and privacy of cloud systems. Existing research in malware detection encounters numerous significant challenges due to the constantly changing and advanced characteristics of malware. Malware detection systems frequently experience high rates of false positives and false negatives, where legitimate applications are incorrectly identified as malware or actual malware remains undetected, which results in operational inefficiencies. Traditional signature-based approaches struggle in recognizing new or modified malware. Additionally, sophisticated malware types, such as file less malware, ransom ware, and rootkits pose detection challenges as they integrate deeply into systems or alter their behaviour to evade detection. These challenges highlight the urgent need for ongoing advancements in this field. Existing methods of malware detection that rely on signatures have been found to be both inefficient and slow in the context of cloud environments. Also, Existing studies have focused on detecting malware by analysing input API calls. But, these models have encountered challenges such as limited accuracy and difficulties in effectively classifying malware types. In contrast, Deep Learning (DL) have shown success by analysing malware behaviour through API calls, which yields encouraging results. Additionally, the data produced by API calls necessitates more computational resources for training. To address these challenges, a new deep learning-based malware detection approach utilizes 2D grayscale images derived from API calls, along with an effective tuning strategy has been proposed. Initially, data are collected from cloud malware dataset. Then, API calls are converted into 2D gray scale images in order to construct gray scale image dataset. After getting the gray scale image, pre-processing is performed to reduce high level noise and to enhance the quality of image by weighted mean filter and anisotropic filter, which helps to improve the performance in classification. Next, these images are then passed into the feature extraction stage to extract sufficient features with an effective integrated densely connected squeeze MobileNet v2 (Ef-DeSMob2), which reduces the dimensionality issue and increase the computational complexity. Then, the collected features are passed into the classification phase to detect normal and malware classes from the samples using sparse attention with residual pyramidal depth wise separable convolutional neural networks (SA:ResPyDSC), which focus to enhance the security and reliability of the model. Finally, the hyper parameters in the classifier model like weights, bias are properly fine-tuned by utilizing hybrid white shark beluga optimization algorithm (Hy-WBeOp). The experimental findings illustrate that the proposed method attains accuracy of 98.06%, precision of 97.99%, recall of 97.05%, f1-score of 96.08% and error metrics like MSE AT 0.08, RMSE of 0.27 and MAE of 0.21, which shows that the proposed method helps to classify the malware classes accurately with less error rates. The proposed approach outperforms with the existing techniques because of its great efficiency. Overall, this approach establish a strong malware detection system classification and enhance the reliability and effectiveness of protection against malicious attacks. [ABSTRACT FROM AUTHOR]

Background: Fundus vessel segmentation is vital for diagnosing ophthalmic diseases like central serous chorioretinopathy (CSC), diabetic retinopathy, and glaucoma. Accurate segmentation provides crucial vessel morphology details, aiding the early detection and intervention of ophthalmic diseases. However, current algorithms struggle with fine vessel segmentation and maintaining sensitivity in complex regions. Challenges also stem from imaging variability and poor generalization across multimodal datasets, highlighting the need for more advanced algorithms in clinical practice. Methods: This paper aims to explore a new vessel segmentation method to alleviate the above problems. We propose a fundus vessel segmentation model based on a combination of double skip connections, deep supervision, and TransUNet, namely DS2TUNet. Initially, the original fundus images are improved through grayscale conversion, normalization, histogram equalization, gamma correction, and other preprocessing techniques. Subsequently, by utilizing the U-Net architecture, the preprocessed fundus images are segmented to obtain the final vessel information. Specifically, the encoder firstly incorporates the ResNetV1 downsampling, dilated convolution downsampling, and Transformer to capture both local and global features, which upgrades its vessel feature extraction ability. Then, the decoder introduces the double skip connections to facilitate upsampling and refine segmentation outcomes. Finally, the deep supervision module introduces multiple upsampling vessel features from the decoder into the loss function, so that the model can learn vessel feature representations more effectively and alleviate gradient vanishing during the training phase. Results: Extensive experiments on publicly available multimodal fundus datasets such as DRIVE, CHASE_DB1, and ROSE-1 demonstrate that the DS2TUNet model attains F1-scores of 0.8195, 0.8362, and 0.8425, with Accuracy of 0.9664, 0.9741, and 0.9557, Sensitivity of 0.8071, 0.8101, and 0.8586, and Specificity of 0.9823, 0.9869, and 0.9713, respectively. Additionally, the model also exhibits excellent test performance on the clinical fundus dataset CSC, with F1-score of 0.7757, Accuracy of 0.9688, Sensitivity of 0.8141, and Specificity of 0.9801 based on the weight trained on the CHASE_DB1 dataset. These results comprehensively validate that the proposed method obtains good performance in fundus vessel segmentation, thereby aiding clinicians in the further diagnosis and treatment of fundus diseases in terms of effectiveness and feasibility. [ABSTRACT FROM AUTHOR]

The multi‐dimensional light‐field manipulation capability of metasurfaces positions them as promising candidates for displaying nanoprinting and holographic images at ultra‐short distances with subwavelength resolution. In recent years, merging nanoprinting and holographic images into a single‐layer metasurface has emerged as a research focus to enhance information storage capacity. However, existing multi‐channel metasurface designs often limit the number of polarization states available for the holographic image. Here, a scheme is proposed and demonstrated to encode both a continuous grayscale image and a vectorial hologram with a continuously varying linear polarization distribution onto a complex amplitude‐modulated metasurface. The nanoprinting and holographic images generated from dielectric metasurface exhibit broadband response for the visible light. This method paves the way for compact optical devices tailored for applications in information encoding, high‐density optical storage, and information anti‐counterfeiting. [ABSTRACT FROM AUTHOR]

Recently, many number of people various countries contracted the COVID-19 (C-19) disease. The identification of this harmful disease and other pneumonia diseases is an important process in the medical world. CT-Scan is mainly prescribed to predict the severity of lung diseases affected by C-19 and other pneumonia diseases. Generally, a CT-Scan image is represented as a grayscale image (GI). Biomedical-oriented GIs are more complex and they are too difficult to recognize the status of lung diseases directly from the experimental images. To address this type of medical problem, a multifractal approach can be applied to analyze and illustrate the GIs in detail. Therefore, the multifractal dimensional analysis is used to diagnose and explore the vehemence of the contamination levels in the lungs. In this study, the complexity of CT-Scan images of C-19 patients is analyzed in order to perform a comparison in terms of age and noise levels. It was also discovered that the intricate of CT-Scan images is considerably varied for patients aged 50 and above when compared to younger subjects. This comparative study indicates that the deadly virus affects elderly persons compared to youngsters. The proposed age-based classification is supported by image processing techniques, qualitative measures, and statistical tools. The obtained results are demonstrated graphically by Generalized Fractal Dimensions (GFD) spectrum, 3D visualization, ANOVA table, and box plots to expose the rate of discrimination of complexity in CT-Scan lung images. [ABSTRACT FROM AUTHOR]

The proliferation of data sharing over the Internet has given rise to pressing concerns surrounding data security. Addressing these concerns, steganography emerges as a viable mechanism to safeguard data during transmission. It involves concealing messages within other media, such as images, exchanged over networks. In this research, we propose an innovative image steganography approach by harnessing the capabilities of bio-inspired algorithms. A central challenge in steganography revolves around the inherent pixel correlations within cover images, which may inadvertently leak sensitive information to potential intruders. To tackle this challenge head-on, we harness the potential of bio-inspired algorithms, which have exhibited promise in efficiently mitigating these vulnerabilities. This paper introduces a steganography strategy rooted in a fusion model that seamlessly integrates diverse bio-inspired algorithms. Our novel embedding approach ensures the production of robust and high-quality cover images and disrupts bit sequences effectively, thereby enhancing resistance against potential attacks. We meticulously evaluate the performance of our method using a comprehensive dataset encompassing grayscale and JPEG color images. Our particular emphasis on color images arises from their superior capacity to conceal a greater volume of information. The results vividly demonstrate our approach's effectiveness in achieving secure and efficient data concealment within images. [ABSTRACT FROM AUTHOR]

Background: To investigate the screening value of a small‐molecule probe to assess the methylation of PAX1 in cervical cancer. Materials and Methods: The diagnostic threshold of the grayscale values for cervical lesions was assessed by plotting the Receiver Operating Characteristic (ROC) curve of subjects. Grayscale values were significantly different among the four groups (p < 0.05). Compared with the LSIL and cervicitis groups, a considerably higher grayscale value was found in the CA and high‐grade squamous intraepithelial lesion (HSIL) groups (both p < 0.05). Results: The differential ROC curves of the grayscale values showed that the diagnostic Area Under Curve of the probe for cervicitis and low‐grade squamous intraepithelial lesion (LSIL) was 0.8724 (95% CI = 0.7762–0.9685, p < 0.0001), for cervicitis and CA was 1.0000 (p < 0.0001), for the LSIL and HSIL was 0.5484 (95% CI = 0.3826–0.7142, p = 0.5755), and for the LSIL and CA was 0.7724 (95% CI = 0.6016–0.9432, p = 0.0138). Conclusion: The small molecular probe has certain application value in differentiating the type of cervical lesions and has better efficacy in distinguishing cervical inflammatory and precancerous lesions from carcinogenesis, but less efficacy in determining the type of precancerous lesions. [ABSTRACT FROM AUTHOR]

Background: Diabetes mellitus affects the whole vascular system, leading to both microvascular and macrovascular complications [1]. Diabetic nephropathy is the dreadful microvascular complication of diabetes mellitus, which lead to end stage kidney disease (ESKD), which increase the risk of cardiovascular mortality [2]. Duplex sonography of the renal artery provides an easily applicable, non-invasive, and well-established way to assess changes in renal vasculature caused by diabetes [5]. In this study, detecting subtle changes in renal vasculature with renal artery Doppler, particularly RI (RESISITIVE INDEX) values, and correlating with biochemical parameters such as creatinine, and urine albumin, helps the physician for accurate management of diabetes patients preventing complications. Objective: Evaluation of renal sono-morphological characteristics using gray scale ultrasound and renal vascular resistance by doppler in patients with diabetic renal disease. Correlation among renal ultrasound, colour doppler, and biochemical parameters in diabetic renal disease. Methods: A time-bound, cross-sectional study, was conducted in the Department of Radio-diagnosis, M.G.M. Medical College and M.Y. Associate Hospital, Indore, Madhya Pradesh, India after receiving approval from Institutional Scientific and Ethical Committee. The duration of the study was from September 2022 to September 2023. A total of 108 patients of type II diabetes mellitus were included in the study. Results: out of total 108 of patients who were diagnosed with type II diabetes mellitus, maximum no of patients (28.7%) in age group of 50-60 years. In our study, male preponderance was observed in our study with 65.74% patients being male. On basis of biochemical parameters divided in 4 subgroups majority of patients 38% were fall under subgroup IV (renal failure) followed by subgroup I(preclinical) 27.8 %, subgroup II (incipient nephropathy) 18.5% and subgroup III (overt nephropathy) 18.5%. Majority of patients in subgroup IV (renal failure) 76.2 to 81.5% revealed gradeII/III renal parenchymal echogenicity changes. In our study most of the patients belonging to subgroup I (80%) had normal RI value while most of the patients belonging to subgroup II (70%), subgroup III (80%) and subgroups IV (94.74%) had increased RI values indicating raised renal vascular resistance as the disease progresses. R.I shows strong positive correlations with Blood Urea Nitrogen (BUN), Urine protein (Alb) and Creatinine levels higher R.I may coincide with elevated levels of these renal function markers. Conclusion: our study demonstrates Renal Doppler is a non-invasive modality that can be used in association with biochemical parameters of patients with diabetic nephropathy. An increasing intra-renal resistive index value could prompt the physician to a more rigid control of blood sugars and hypertension in this subgroup of diabetic patients delaying the progression to end-stage renal failure. [ABSTRACT FROM AUTHOR]

Statistics teaching at the high school level needs modernizing to include digital sources of data that students interact with every day. Algorithmic modeling approaches are recommended, as they can support the teaching of data science and computational thinking. Research is needed about the design of tasks that support high school statistics teachers to learn new statistical and computational approaches such as digital image analysis and classification models. Using our design framework, the construction of a task is described that introduces classification modeling using grayscale digital images. The task was implemented within a teaching experiment involving six high school statistics teachers. Our findings from this exploratory study indicated that the task design seemed to support statistical and computational thinking practices related to classification modeling and digital image data. [ABSTRACT FROM AUTHOR]

A novel colorimetric approach specifically designed to effectively identify the presence of 3-aminophenol (3-AP) in environmental water is introduced. Briefly, a nitrogen-doped carbon-supported cobalt nanozyme (Co@CN-1) was synthesized and utilized to improve the oxidation of 3,3',5,5'-tetramethylbenzidine (TMB) in the presence of peroxymonosulfate (PMS). Comparative catalytic reactions confirmed that the performance of PMS as an activator exceeds that of hydrogen peroxide catalytically by a factor of 3.5. The catalytic reaction parameters underwent optimization, further resulting in the derivation of a linear detection equation for 3-AP, expressed as inhibition rate (IR%) = 3.35[3-AP]—4.36 (0–20 μM, R2 = 0.994) and IR% = 1.43[3-AP] + 31.87 (20–36 μM, R2 = 0.992), with the limit of detection (LOD) of 2.84 μM. The linear relationship between 3-AP concentration and the conversion of color to grayscale value (GSV) was established by smartphones, expressed as GSV = 1.28[3-AP] + 147.10 (R2 = 0.972). Density functional theory calculations revealed that Co acts as the preferred active site for donating electrons in PMS activation. This work provides a rapid and accurate approach for monitoring 3-AP concentration, enabling real-time analysis and potentially contributing to environmental and ecological studies. [ABSTRACT FROM AUTHOR]

Defect detection on steel surfaces with complex textures is a critical and challenging task in the industry. The limited number of defect samples and the complexity of the annotation process pose significant challenges. Moreover, performing defect segmentation based on accurate identification further increases the task's difficulty. To address this issue, we propose VQGNet, an unsupervised algorithm that can precisely recognize and segment defects simultaneously. A feature fusion method based on aggregated attention and a classification-aided module is proposed to segment defects by integrating different features in the original images and the anomaly maps, which direct the attention to the anomalous information instead of the irregular complex texture. The anomaly maps are generated more confidently using strategies for multi-scale feature fusion and neighbor feature aggregation. Moreover, an anomaly generation method suitable for grayscale images is introduced to facilitate the model's learning on the anomalous samples. The refined anomaly maps and fused features are both input into the classification-aided module for the final classification and segmentation. VQGNet achieves state-of-the-art (SOTA) performance on the industrial steel dataset, with an I-AUROC of 99.6%, I-F1 of 98.8%, P-AUROC of 97.0%, and P-F1 of 80.3%. Additionally, ViT-Query demonstrates robust generalization capabilities in generating anomaly maps based on the Kolektor Surface-Defect Dataset 2. [ABSTRACT FROM AUTHOR]

In the field of welding detection, weld bead cross-section morphology serves as a crucial indicator for analyzing welding quality. However, the extraction of weld bead cross-section morphology often relies on manual extraction based on human expertise, which can be limited in consistency and operational efficiency. To address this issue, this paper proposes a multi-layer multi-pass weld bead cross-section morphology extraction method based on row–column grayscale segmentation. The weld bead cross-section morphology image is pre-processed and then segmented into rows and columns based on the average gray value of the image. In order to extract the feature of multi-layer multi-pass weld feature images, an outline showing the binarization threshold is selected for each segmented image (ESI). Then, the weld contour of ESI is extracted before image fusion and morphological processing. Finally, the weld feature parameters (circumference, area, etc.) are extracted from the obtained weld feature image. The results indicate that the relative errors in circumference and area are within 10%, while the discrepancies in maximum weld seam width and maximum weld seam height can be close to the true value. The quality assessment falls within a reasonable range, the average value of SSIM is above 0.9 and the average value of PSNR is above 60 on average. The results demonstrate that this method is feasible for extracting the general contour features of multi-layer multi-pass weld bead cross-section morphology images, providing a basis for further detailed analysis and improvement in welding quality assessment. [ABSTRACT FROM AUTHOR]

Aiming to solve the challenges of difficult training, mode collapse in current generative adversarial networks (GANs), and the efficiency issue of requiring multiple samples for Denoising Diffusion Probabilistic Models (DDPM), this paper proposes a satellite remote sensing grayscale image colorization method using a denoising GAN. Firstly, a denoising optimization method based on U-ViT for the generator network is introduced to further enhance the model's generation capability, along with two optimization strategies to significantly reduce the computational burden. Secondly, the discriminator network is optimized by proposing a feature statistical discrimination network, which imposes fewer constraints on the generator network. Finally, grayscale image colorization comparative experiments are conducted on three real satellite remote sensing grayscale image datasets. The results compared with existing typical colorization methods demonstrate that the proposed method can generate color images of higher quality, achieving better performance in both subjective human visual perception and objective metric evaluation. Experiments in building object detection show that the generated color images can improve target detection performance compared to the original grayscale images, demonstrating significant practical value. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Topological analysis is widely adopted in various research fields to unveil intricate features and structural relationships implied in geometrical objects. Especially, in the fields of data analysis, exploring the topological properties of various images offers rich insights into the intrinsic geometrical information within them. In this study, a novel approach is proposed to investigate the topological properties of arbitrary grayscale images by employing a straightforward procedure used in 2D magnetism studies to calculate topological numbers. This method utilizes machine learning techniques to transfer chiral magnetic textures onto the images. Then, the topological number is then computed directly from the converted images by integrating the solid angles formed by adjacent spin vectors. The method successfully identifies the topological numbers of various grayscale images, showing stable performances against small noises. Furthermore, two applications of the method: are demonstrated topological analysis of the Modified National Institute of Standards and Technology (MNIST) dataset and the counting of blood cells in microscopic images. [ABSTRACT FROM AUTHOR]

To reveal the effects of illuminance and spectral band changes on coal and gangue image and spectral parameters, and to provide fundamental data for using multispectral images in coal and gangue recognition research, this paper analyzes image parameters (standard deviation, skewness, entropy, and contrast) and the spectral parameter using experimental methods, and compares the differences between coal and gangue parameter values. First, we analyze the variations of parameters, and find that as illuminance increases, the image parameters fluctuate in shorter spectral bands but change slightly in longer ones, while the spectral parameter increases across all bands; as wavelength increases, the image parameters rise or fluctuate within 546–622 nm, while the spectral parameter increases; in other bands, all parameters initially decrease before stabilizing. Second, we compare parameter deviation by normalizing coal and gangue values, and find that coal and gangue have the largest deviation in the spectral parameter, and the smallest in skewness; they have the largest fluctuation range in entropy, and the smallest in skewness; image parameters are more sensitive to changes in illuminance and spectral bands than the spectral parameter; and the deviations in both image and spectral parameters are larger at 7000lux and 585 nm than at other settings. [ABSTRACT FROM AUTHOR]

Purpose: This study aimed to assess reliable options for bedside diagnosis of silent aspiration in the intensive care unit by examining the use of default grayscale images (DGI) obtained using a mobile, general-purpose, radiography system capable of dynamic digital radiography (M-DDR) and inverted grayscale images (IGI) of DGI. Methods: This cohort study (exploratory and preliminary) involved 18 adult patients (mean age, 89.0 years) for whom a swallowing assessment request was received from their primary physicians. Fifty-six IGI videoclips were evaluated by three specialists using the penetration-aspiration scale (PAS), with the gold standard being the consensus reading of all three specialists. Another three speech-language pathologists (SLPs) assessed 56 DGI and IGI videoclips using the PAS. PAS scores 1 and 2 were classified as normal range, PAS scores 3–5 as pathological laryngeal penetration, and PAS scores 6–8 as aspiration. The correct rates with IGI and DGI were then determined, and the level of agreement of IGI and DGI evaluations was evaluated. Results: The correct rate of all evaluators was 100% for normal range, 80–100% for pathological laryngeal penetration, and 83–100% for aspiration with IGI and 100% for normal range, 90% for pathological laryngeal penetration, and 83% for aspiration with DGI. The kappa coefficient for IGI and DGI showed almost complete agreement for abnormal conditions. Conclusion: Dynamic imaging of swallowing 2–5 ml of liquid using M-DDR performed for elderly patients at the bedside showed that aspiration assessments by SLPs obtained from DGI videos immediately after imaging are acceptable. [ABSTRACT FROM AUTHOR]

The objective of this study was to assess the utility of narrow-band imaging (NBI) for improving intraneural dissection during gross total resection of head and neck schwannoma. Specifically, we aimed to quantitatively evaluate whether NBI can enhance the identification of pseudocapsule and true capsule within the tumor. Nine schwannoma surgery cases conducted between February 2018 and October 2022 were retrospectively analyzed. The surgical procedures followed established principles with a specific focus on utilizing NBI to distinguish between the pseudocapsule and true capsule. Intraneural dissection was performed by searching for a tumor surface with a fascicle-free window, followed by longitudinal incision of the pseudocapsule. NBI was used to distinguish between the pseudocapsule and true capsule. Surgical views were captured under both white light (WL) illumination and NBI for further analysis. The brightness and contrast of the pseudocapsule and true capsule were quantitatively measured using ImageJ and were compared. Under NBI, the pseudocapsule consistently appeared greenish-gray, whereas the true capsule exhibited a white appearance. Quantitative analysis revealed a statistically significant difference (p < 0.0001) in brightness between the pseudocapsule (mean grayscale value 52.1, 95%CI; 46.4–75.3) and true tumor capsule (mean grayscale value 120.8, 95%CI; 155.7–109.0) under NBI. Conversely, there was no statistically significant difference in the brightness of these structures under WL (p = 0.2067). NBI also showed significantly higher contrast between the two structures than did WL (contrast 73.6, 95%CI; 53.1–89.5 vs. 30.9, 95%CI; 1.0–47.5, p = 0.0034). Further spectral analysis revealed that the most substantial difference in brightness between the pseudocapsule and the true tumor capsule was observed in the red spectrum, with a difference in brightness of −0.6 (95%CI; −16.8–14.8) under WL and 83.5 (95%CI; 50.3–100.0) under NBI (p < 0.0001). NBI proved to be a valuable tool for enhancing the identification of pseudocapsule and true capsule during intraneural dissection in head and neck schwannoma surgery. The improved contrast and membrane visibility offered by NBI might have the potential to reduce postoperative neurological deficits and improve surgical outcomes. Further research is warranted to validate our findings and explore the broader applications of NBI in schwannoma surgery. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Copyright of Saudi Medical Journal is the property of Saudi Medical Journal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To address the issues of low accuracy and high false positive rate in traditional Otsu algorithm for defect detection on infrared images of wind turbine blades (WTB), this paper proposes a technique that combines morphological image enhancement with an improved Otsu algorithm. First, mathematical morphology’s differential multi-scale white and black top-hat operations are applied to enhance the image. The algorithm employs entropy as the objective function to guide the iteration process of image enhancement, selecting appropriate structural element scales to execute differential multi-scale white and black top-hat transformations, effectively enhancing the detail features of defect regions and improving the contrast between defects and background. Afterwards, grayscale inversion is performed on the enhanced infrared defect image to better adapt to the improved Otsu algorithm. Finally, by introducing a parameter K to adjust the calculation of inter-class variance in the Otsu method, the weight of the target pixels is increased. Combined with the adaptive iterative threshold algorithm, the threshold selection process is further fine-tuned. Experimental results show that compared to traditional Otsu algorithms and other improvements, the proposed method has significant advantages in terms of defect detection accuracy and reducing false positive rates. The average defect detection rate approaches 1, and the average Hausdorff distance decreases to 0.825, indicating strong robustness and accuracy of the method. [ABSTRACT FROM AUTHOR]

This paper proposes a new approach to counter cyberattacks using the increasingly diverse malware in cyber security. Traditional signature detection methods that utilize static and dynamic features face limitations due to the continuous evolution and diversity of new malware. Recently, machine learning-based malware detection techniques, such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), have gained attention. While these methods demonstrate high performance by leveraging static and dynamic features, they are limited in detecting new malware or variants because they learn based on the characteristics of existing malware. To overcome these limitations, malware detection techniques employing One-Shot Learning and Few-Shot Learning have been introduced. Based on this, the Siamese Network, which can effectively learn from a small number of samples and perform predictions based on similarity rather than learning the characteristics of the input data, enables the detection of new malware or variants. We propose a dual Siamese network-based detection framework that utilizes byte images converted from malware binary data to grayscale, and opcode frequency-based images generated after extracting opcodes and converting them into 2-gram frequencies. The proposed framework integrates two independent Siamese network models, one learning from byte images and the other from opcode frequency-based images. The detection models trained on the different kinds of images generated separately apply the L1 distance measure to the output vectors the models generate, calculate the similarity, and then apply different weights to each model. Our proposed framework achieved a malware detection accuracy of 95.9% and 99.83% in the experiments using different malware datasets. The experimental results demonstrate that our malware detection model can effectively detect malware by utilizing two different types of features and employing the dual Siamese network-based model. [ABSTRACT FROM AUTHOR]

A new steganographic method by pixel-value differencing (PVD) using general quantization ranges of pixel pairs' difference values is proposed. The objective of this method is to provide a data embedding technique with a range table with range widths not limited to powers of 2, extending PVD-based methods to enhance their flexibility and data-embedding rates without changing their capabilities to resist security attacks. Specifically, the conventional PVD technique partitions a grayscale image into 1 × 2 non-overlapping blocks. The entire range [0, 255] of all possible absolute values of the pixel pairs' grayscale differences in the blocks is divided into multiple quantization ranges. The width of each quantization range is a power of two to facilitate the direct embedding of the bit information with high embedding rates. Without using power-of-two range widths, the embedding rates can drop using conventional embedding techniques. In contrast, the proposed method uses general quantization range widths, and a multiple-based number conversion mechanism is employed skillfully to implement the use of non-power-of-two range widths, with each pixel pair being employed to embed a digit in the multiple-based number. All the message bits are converted into a big multiple-based number whose digits can be embedded into the pixel pairs with a higher embedding rate. Good experimental results showed the feasibility of the proposed method and its resistance to security attacks. In addition, implementation examples are provided, where the proposed method adopts non-power-of-two range widths and employs multiple-based number conversion to expand the data-hiding and steganalysis-resisting capabilities of other PVD methods. [ABSTRACT FROM AUTHOR]

Background: Temperature prediction is crucial in the clinical ablation treatment of liver cancer, as it can be used to estimate the coagulation zone of microwave ablation. Methods: Experiments were conducted on 83 fresh ex vivo porcine liver tissues at two ablation powers of 15 W and 20 W. Ultrasound grayscale images and temperature data from multiple sampling points were collected. The machine learning method of random forests was used to train the selected texture features, obtaining temperature prediction models for sampling points and the entire ultrasound imaging area. The accuracy of the algorithm was assessed by measuring the area of the hyperechoic area in the porcine liver tissue cross-section and ultrasound grayscale images. Results: The model exhibited a high degree of accuracy in temperature prediction and the identification of coagulation zone. Within the test sets for the 15 W and 20 W power groups, the average absolute error for temperature prediction was 1.14°C and 4.73°C, respectively. Notably, the model's accuracy in measuring the area of coagulation was higher than that of traditional ultrasonic grey-scale imaging, with error ratios of 0.402 and 0.182 for the respective power groups. Additionally, the model can filter out texture features with a high correlation to temperature, providing a certain degree of interpretability. Conclusion: The temperature prediction model proposed in this study can be applied to temperature monitoring and coagulation zone range assessment in microwave ablation. [ABSTRACT FROM AUTHOR]

In the field of medical imaging, there is a strong requirement for the storage of an immense volume of digitized medical image data. The digital image must be compressed heavily before storing and transferring it because of having restricted bandwidth and scope of storage. When compression of images is done at a lower bit rate it reduces the image fidelity that results in a drop in quality but poses many challenges to overcome and prevents diagnostic miscalculations with great compression rates for reduced storage and quick transmission. To overcome this challenging issue several hybrid efficient compression procedures solely for medical digital images have been introduced in recent years. The transformation of image, quantization, and encoding is part of image compression. This paper presents a qualitative and comprehensive review of image compression techniques for two-dimensional (2D) still and three-dimensional (3D) medical images. The features and constraints associated with various compression methods for compressing grayscale images are reviewed and discussed in this paper. In-depth reviews of the practical concerns and difficulties in the medical scan compression arena are provided. [ABSTRACT FROM AUTHOR]

Secure transfer of digital images is an important issue in modern image communications. The complexity of encryption algorithms and their key space is a guarantee for security and robustness issues, and the algorithms are competing in this regard while considering time complexity constraints. In this paper, it is tried to increase the encryption complexity and unpredictability of the encryption scheme using different phases of chaos game representation (GCR), logistic map diffusion, and convolutional auto-encoder-based image representation. In the proposed scheme, the original image's pixels are first turned into a binary sequence, after which the CGR algorithm is applied to create a sequence of coordinates in the CGR space. These coordinates are used as the first key, and the pixels of the original image are aligned with this key. Additionally, the second key is generated using the chaotic logistic map to increase the complexity of the key. After that, a randomly weighted convolutional auto-encoder is applied, and the encrypted image resulting from the first two stages is fed to the network for simultaneous diffusion and compression for further complexity increment. The applied convolutional auto-encoder does not require training, and it offers a significant amount of key space, which helps robustness against various attacks. Resulting from the experiments, the average entropy of the encrypted images is relatively high, while the considerable value of the NPCR and UACI criteria denotes the robustness of the approach against differential attacks. This algorithm has demonstrated superiority on both grayscale and color images. [ABSTRACT FROM AUTHOR]

Bubble detection in water plays important roles in human exploration and management of the ocean. This research presents a detection technique based on laser polarization dual-mode fusion, aiming at solving the difficulties of light scattering intensity characteristics that are hard to extract and the small particle size of underwater bubbles that are hard to detect. To increase the precision of bubble identification, an image fusion technique based on bubble polarization degree is first presented. Second, we quantitatively investigate the grayscale undulation of bubbles with different size and number distributions in the image from both statistical and experimental aspects, introduce image grayscale fluctuation (GF) to fuse two modes of laser polarization and the image, establish an a posteriori distribution probability model of discriminating features such as the size and number of bubbles, and realize the bubble small-sample, multi-source data fitting. The findings demonstrate that dynamic bubble detection in the 50–1000 μm and 100–2000 cm−3 ranges can achieve more than 95%, as well as more than a 93%, accuracy in quantity distribution and bubble size change. This technique achieves the continuous perception of bubble features in complicated underwater environments, and offers a possible application scheme for the detection of marine bubble environments. [ABSTRACT FROM AUTHOR]

The infrared image colorization technique overcomes the limitation of grayscale characteristics of infrared images and achieves cross-modal conversion between infrared and visible images. Aiming at the problem of lack of infrared-visible pairing data, existing studies usually adopt unsupervised learning methods based on contrastive loss. Due to significant differences between modalities, reliance on contrastive loss alone hampers the learning of accurate semantic features. In this paper, we propose DC-Net, which is a dual-branch contrastive learning network that combines perceptual features and multiscale residual attention for the unsupervised cross-modal transformation of infrared to visible images. The network comprises a patch-wise contrastive guidance branch (PwCGB) and a perceptual contrastive guidance branch (PCGB). PwCGB focuses on discerning feature similarities and variances across image patches, synergizing patch-wise contrastive loss with adversarial loss to adaptively learn local structure and texture. In addition, we design a multiscale residual attention generator to capture richer features and adaptively integrate multiscale information. PCGB introduces a novel perceptual contrastive loss that uses perceptual features from pre-trained VGG16 models as positive and negative samples. This helps the network align colorized infrared images with visible images in the high-level feature space, improving the semantic accuracy of the colorized infrared images. Our unsupervised infrared image colorization method achieves a PSNR of 16.833 and an SSIM of 0.584 on the thermal infrared dataset and a PSNR of 18.828 and an SSIM of 0.685 on the near-infrared dataset. Compared to existing algorithms, it demonstrates substantial improvements across all metrics, validating its effectiveness. [ABSTRACT FROM AUTHOR]

In this paper, we introduce an efficient lossy coding procedure specifically tailored for handling video sequences of automotive high-dynamic range (HDR) image sensors in advanced driver-assistance systems (ADASs) for autonomous vehicles. Nowadays, mainly for security reasons, lossless compression is used in the automotive industry. However, it offers very low compression rates. To obtain higher compression rates, we suggest using lossy codecs, especially when testing image processing algorithms in software in-the-loop (SiL) or hardware-in-the-loop (HiL) conditions. Our approach leverages the high-quality VP9 codec, operating in two distinct modes: grayscale image compression for automatic image analysis and color (in RGB format) image compression for manual analysis. In both modes, images are acquired from the automotive-specific RCCC (red, clear, clear, clear) image sensor. The codec is designed to achieve a controlled image quality and state-of-the-art compression ratios while maintaining real-time feasibility. In automotive applications, the inherent data loss poses challenges associated with lossy codecs, particularly in rapidly changing scenes with intricate details. To address this, we propose configuring the lossy codecs in variable bitrate (VBR) mode with a constrained quality (CQ) parameter. By adjusting the quantization parameter, users can tailor the codec behavior to their specific application requirements. In this context, a detailed analysis of the quality of lossy compressed images in terms of the structural similarity index metric (SSIM) and the peak signal-to-noise ratio (PSNR) metrics is presented. With this analysis, we extracted some codec parameters, which have an important impact on preservation of video quality and compression ratio. The proposed compression settings are very efficient: the compression ratios vary from 51 to 7765 for grayscale image mode and from 4.51 to 602.6 for RGB image mode, depending on the specified output image quality settings. We reached 129 frames per second (fps) for compression and 315 fps for decompression in grayscale mode and 102 fps for compression and 121 fps for decompression in the RGB mode. These make it possible to achieve a much higher compression ratio compared to lossless compression while maintaining control over image quality. [ABSTRACT FROM AUTHOR]

Malware attacks have a cascading effect, causing financial harm, compromising privacy, operations and interrupting. By preventing these attacks, individuals and organizations can safeguard the valuable assets of their operations, and gain more trust. In this paper, we propose a dual convolutional neural network (DCNN) based architecture for malware classification. It consists first of converting malware binary files into 2D grayscale images and then training a customized dual CNN for malware multi-classification. This paper proposes an efficient approach for malware classification using dual CNNs. The model leverages the complementary strengths of a custom structure extraction branch and a pre-trained ResNet-50 model for malware image classification. By combining features extracted from both branches, the model achieved superior performance compared to a single-branch approach. [ABSTRACT FROM AUTHOR]

Materials that provide dynamically tunable infrared (IR) response are important for many applications, including active camouflage and thermal management. However, current IR-tunable systems often exhibit limitations in mechanical properties or practicality of their tuning modalities, or require complex and costly fabrication methods. An additional challenge relates to providing compatibility between different spectral channels, such as allowing an object to be reversibly concealed in the IR without making it appear in the visible range. Here, we demonstrate that conducting polymer-cellulose papers, fabricated through a simple and cheap approach, can overcome such challenges. The papers exhibit IR properties that can be electrochemically tuned with large modulation (absolute emissivity modulation of 0.4) while maintaining largely constant response in the visible range. Owing to high ionic and electrical conductivity, the tuning of the top surface can be performed electrochemically from the other side of the paper even at tens of micrometer thicknesses, removing the need for overlaying electrode and electrolyte in the optical beam path. These features enabled a series of electrically tunable IR devices, where we focus on demonstrating dynamic radiative coolers, thermal camouflage, anti-counterfeiting tags, and grayscale IR displays. The conducting polymer-cellulose papers are sustainable, cheap, flexible and mechanically robust, providing a versatile materials platform for active and adaptive IR optoelectronic devices. [ABSTRACT FROM AUTHOR]

The physics of notations (PoN) is a framework for designing cognitively effective notations. Cognitive effectiveness refers to the ease (speed and accuracy) by which model readers read models. In 2019, a PoN‐Enabled notation for use case diagrams was proposed. It has been empirically proven that the cognitive effectiveness of this new notation is superior to the original use case notation. The new notation however relies in part on the use of color. The accessibility of this new design has not been validated for use by the colorblind community, or any users who need to use a grayscale version of the models created. The PoN framework was not designed to explicitly account for the colorblind community or users who can only access grayscale versions of models. Inclusivity should not be an afterthought in software engineering practice or research. To this end, this paper empirically evaluates the cognitive effectiveness of the PoN‐enabled use case notation in situations where it is viewed in grayscale. [ABSTRACT FROM AUTHOR]

Motivation Structural variants (SVs) play an important role in genetic research and precision medicine. As existing SV detection methods usually contain a substantial number of false positive calls, approaches to filter the detection results are needed. Results We developed a novel deep learning-based SV filtering tool, CSV-Filter, for both short and long reads. CSV-Filter uses a novel multi-level grayscale image encoding method based on CIGAR strings of the alignment results and employs image augmentation techniques to improve SV feature extraction. CSV-Filter also utilizes self-supervised learning networks for transfer as classification models, and employs mixed-precision operations to accelerate training. The experiments showed that the integration of CSV-Filter with popular SV detection tools could considerably reduce false positive SVs for short and long reads, while maintaining true positive SVs almost unchanged. Compared with DeepSVFilter, a SV filtering tool for short reads, CSV-Filter could recognize more false positive calls and support long reads as an additional feature. Availability and implementation https://github.com/xzyschumacher/CSV-Filter [ABSTRACT FROM AUTHOR]

In recent research, dendritic neuron-based models have shown promise in effectively learning and recognizing object motion direction within binary images. Leveraging the dendritic neuron structure and On–Off Response mechanism within the primary cortex, this approach has notably reduced learning time and costs compared to traditional neural networks. This paper advances the existing model by integrating bio-inspired components into a learnable dendritic neuron-based artificial visual system (AVS), specifically incorporating mechanisms from horizontal and bipolar cells. This enhancement enables the model to proficiently identify object motion directions in grayscale images, aligning its threshold with human-like perception. The enhanced model demonstrates superior efficiency in motion direction recognition, requiring less data (90% less than other deep models) and less time for training. Experimental findings highlight the model's remarkable robustness, indicating significant potential for real-world applications. The integration of bio-inspired features not only enhances performance but also opens avenues for further exploration in neural network research. Notably, the application of this model to realistic object recognition yields convincing accuracy at nearly 100%, underscoring its practical utility. [ABSTRACT FROM AUTHOR]

Electric motors play a crucial role in self-driving vehicles. Therefore, fault diagnosis in motors is important for ensuring the safety and reliability of vehicles. In order to improve fault detection performance, this paper proposes a motor fault diagnosis method based on vibration signals. Firstly, the vibration signals of each operating state of the motor at different frequencies are measured with vibration sensors. Secondly, the characteristic of Gram image coding is used to realize the coding of time domain information, and the one-dimensional vibration signals are transformed into grayscale diagrams to highlight their features. Finally, the lightweight neural network Xception is chosen as the main tool, and the attention mechanism Convolutional Block Attention Module (CBAM) is introduced into the model to enforce the importance of the characteristic information of the motor faults and realize their accurate identification. Xception is a type of convolutional neural network; its lightweight design maintains excellent performance while significantly reducing the model's order of magnitude. Without affecting the computational complexity and accuracy of the network, the CBAM attention mechanism is added, and Gram's corner field is combined with the improved lightweight neural network. The experimental results show that this model achieves a better recognition effect and faster iteration speed compared with the traditional Convolutional Neural Network (CNN), ResNet, and Xception networks. [ABSTRACT FROM AUTHOR]

Background: Value analysis of a small‐molecule fluorescent probe for methylation detection in different cervical lesions. Materials and Methods: (1) The grayscale values of distinct lesion tissues were remarkably distinct among the four groups (p < 0.05). The comparison of the grayscale value between the two groups showed that the CA group noticeably exceeded the LSIL and cervicitis groups, and the HSIL group was apparently higher than the LSIL and cervicitis groups (p < 0.05); (2) The mean grayscale values of the enrolled subjects were calculated with 55.21 as the midline, with >55.21 as positive and ≤55.21 as negative. Results: The results showed that the positive rate of the cervicitis group was 0.00%, the LSIL group 67.74%, the HSIL group 83.33%, and the CA group 100.00%. The results among the four groups were notably distinct (p < 0.05); (3) The comparison among DAPI, probe, bright, and merged images of cervicitis, LSIL, HSIL, and CA indicated that different cervical lesions were with quite various stains. Conclusion: The grayscale value, positive rate, and stained picture of distinct cervical lesions were remarkably different. The small‐molecule fluorescent probe has a good value in differentiating cervical lesions and can be considered for popularization and application. [ABSTRACT FROM AUTHOR]

Scientific articles published prior to the "age of digitization" in the late 1990s contain figures which are "trapped" within their scanned pages. While progress to extract figures and their captions has been made, there is currently no robust method for this process. We present a YOLO-based method for use on scanned pages, after they have been processed with Optical character recognition (OCR), which uses both grayscale and OCR features. We focus our efforts on translating the intersection-over-union (IOU) metric from the field of object detection to document layout analysis and quantify "high localization" levels as an IOU of 0.9. When applied to the astrophysics literature holdings of the NASA astrophysics data system, we find F1 scores of 90.9% (92.2%) for figures (figure captions) with the IOU cut-off of 0.9 which is a significant improvement over other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Estimating the missing data from an incomplete measurement or observation plays an important role in the area of big data analytic, especially for some streaming data analysis such as video streaming recovery, traffic data analysis and network engineering. In this paper, by making full use of the potential spatio-temporal smoothness and inherent correlation properties in real-world tensor data, we present a low-rank Tensor Train (TT) factorization method for solving the 3-way streaming low-rank tensor completion problems. Extensive numerical experiments on color images, network traffic data and gray scale videos show that our model outperforms many existing state-of-the-art approaches in terms of achieving higher recovery accuracy. [ABSTRACT FROM AUTHOR]

Timely discovery and disposal of road risk sources constitute the cornerstone of road operation safety. Presently, the detection of road risk sources frequently relies on manual inspections via inspection vehicles, a process that is both inefficient and time-consuming. To tackle this challenge, this paper introduces a novel automated approach for detecting road risk sources, termed the multi-scale lightweight network (MSLN). This method primarily focuses on identifying road surfaces, potholes, and scattered objects. To mitigate the influence of real-world factors such as noise and uneven brightness on test results, pavement images were carefully collected. Initially, the collected images underwent grayscale processing. Subsequently, the median filtering algorithm was employed to filter out noise interference. Furthermore, adaptive histogram equalization techniques were utilized to enhance the visibility of cracks and the road background. Following these preprocessing steps, the MSLN model was deployed for the detection of road risk sources. Addressing the challenges associated with two-stage network models, such as prolonged training and testing times, as well as deployment difficulties, this study adopted the lightweight feature extraction network MobileNetV2. Additionally, transfer learning was incorporated to elevate the model's training efficiency. Moreover, this paper established a mapping relationship model that transitions from the world coordinate system to the pixel coordinate system. This model enables the calculation of risk source dimensions based on detection outcomes. Experimental results reveal that the MSLN model exhibits a notably faster convergence rate. This enhanced convergence not only boosts training speed but also elevates the precision of risk source detection. Furthermore, the proposed mapping relationship coordinate transformation model proves highly effective in determining the scale of risk sources. [ABSTRACT FROM AUTHOR]

Long-strip imaging is an important way of improving the coverage and acquisition efficiency of remote sensing satellite data. During the agile maneuver imaging process of the satellite, the LuoJia3-01 satellite can obtain a sequence of array long-strip images with a certain degree of overlap. Limited by the relative accuracy of satellite attitude, there will be relative misalignment between the sequence frame images, requiring high-precision geometric processing to meet the requirements of large-area remote sensing applications. Therefore, this study proposes a new method for the geometric correction of long-strip images without ground control points (GCPs) through GPU acceleration. Firstly, through the relative orientation of sequence images, the relative geometric errors between the images are corrected frame-by-frame. Then, block perspective transformation and image point densified filling (IPDF) direct mapping processing are carried out, mapping the sequence images frame-by-frame onto the stitched image. In this way, the geometric correction and image stitching of the sequence frame images are completed simultaneously. Finally, computationally intensive steps, such as point matching, coordinate transformation, and grayscale interpolation, are processed in parallel using GPU to further enhance the program's execution efficiency. The experimental results show that the method proposed in this study achieves a stitching accuracy of less than 0.3 pixels for the geometrically corrected long-strip images, an internal geometric accuracy of less than 1.5 pixels, and an average processing time of less than 1.5 s per frame, meeting the requirements for high-precision near-real-time processing applications. [ABSTRACT FROM AUTHOR]

Background: Endoscopy image enhancement technology provides doctors with clearer and more detailed images for observation and diagnosis, allowing doctors to assess lesions more accurately. Unlike most other endoscopy images, cystoscopy images face more complex and diverse image degradation because of their underwater imaging characteristics. Among the various causes of image degradation, the blood haze resulting from bladder mucosal bleeding make the background blurry and unclear, severely affecting diagnostic efficiency, even leading to misjudgment. Materials and Methods: We propose a deep learning-based approach to mitigate the impact of blood haze on cystoscopy images. The approach consists of two parts as follows: a blood haze removal network and a contrast enhancement algorithm. First, we adopt Feature Fusion Attention Network (FFA-Net) and transfer learning in the field of deep learning to remove blood haze from cystoscopy images and introduce perceptual loss to constrain the network for better visual results. Second, we enhance the image contrast by remapping the gray scale of the blood haze-free image and performing weighted fusion of the processed image and the original image. Results: In the blood haze removal stage, the algorithm proposed in this article achieves an average peak signal-to-noise ratio of 29.44 decibels, which is 15% higher than state-of-the-art traditional methods. The average structural similarity and perceptual image patch similarity reach 0.9269 and 0.1146, respectively, both superior to state-of-the-art traditional methods. Besides, our method is the best in keeping color balance after removing the blood haze. In the image enhancement stage, our algorithm enhances the contrast of vessels and tissues while preserving the original colors, expanding the dynamic range of the image. Conclusion: The deep learning-based cystoscopy image enhancement method is significantly better than other traditional methods in both qualitative and quantitative evaluation. The application of artificial intelligence will provide clearer, higher contrast cystoscopy images for medical diagnosis. [ABSTRACT FROM AUTHOR]

Sonography with its non-invasive and deep tissue-penetrating characteristics, not only contributes to promising developments in clinical disease diagnosis but also obtains acknowledgments as a prospective therapeutic approach in the field of tumor treatment. However, it remains a challenge for sonography simultaneously to achieve efficient imaging and therapeutic functionality. Here, we present an innovative integrated diagnosis and treatment paradigm by developing the nanomedicine of percarbamide-bromide-mesoporous organosilica spheres (MOS) with RGD peptide modification (PBMR) by loading percarbamide and bromide in MOS which were prepared by a one-step O/W microemulsion method. The PBMR nanomedicine effectively modifies the tumor acoustic environment to improve sonoimaging efficacy and induces sonochemical reactions to enhance the production of reactive oxygen species (ROS) for tumor treatment efficiency under sonography. The combination of PBMR nanomedicine and SDT achieved multiple ROS generation through the controlled sonochemical reactions and significantly boosted the potency of sonodynamic therapy and induced significant tumor regression with non-invasive tissue penetrability and minimizing damage to healthy tissues. Simultaneously, the generation of oxygen gas in the sonochemical process augments ultrasound reflection, resulting in a 4.9-fold increase in imaging grayscale. Our research establishes an effective platform for the synergistic integration of sonoimaging and sonodynamic antitumor therapy, offering a novel approach for precise antitumor treatment in the potential clinical applications. [ABSTRACT FROM AUTHOR]

Summary: During harvesting, transportation and storage of kiwifruit, the flesh is often bruised by collision or compression. However, the bruises in kiwifruit are extremely difficult to recognise by naked eyes and are called hidden bruises. Accordingly, a fast method for detecting hidden bruises in kiwifruit was developed in this study based on hyperspectral imaging (HSI) coupled with deep learning. The spectral range (924–1277 nm) and feature wavelengths (928.19, 1051.03 and 1190.47 nm) sensitive to hidden bruises in kiwifruit were selected using the principal component analysis (PCA). Subsequently, three‐channel images (Dataset 1), grayscale images (Dataset 2) and pseudo‐colour images (Dataset 3) were generated according to the images of feature wavelengths of the kiwifruit. The YOLOv5s model for detecting the hidden bruised areas of the kiwifruit was developed using these three datasets. The results showed that the YOLOv5s detection model performed best at Dataset 1, and the values of Precision, Recall, F1, mAP and FNR of this model were 98.25%, 97.50%, 97.87%, 99.12% and 2.50% respectively. The study showed that HSI technology combined with the YOLOv5s model can effectively detect hidden bruises in kiwifruit, providing references for detecting hidden bruises in other fruit. [ABSTRACT FROM AUTHOR]

Residual dosage has a significant impact on the settling characteristics of coal slurry flocs and the sedimentation efficiency of coal slurry. This study conducted sedimentation stirring experiments to measure the supernatant grayscale, floc size, settling velocity, and residual anionic polyacrylamide (APAM) under varying energy inputs. The investigation focused on the correlation between different levels of APAM residual and the settling characteristics of coal slurry flocs. The results show that having APAM residuals in the first three stages helps with sedimentation. This leads to lower residual levels, higher grayscale in the supernatant, bigger floc sizes, and better settling velocities. However, in the fourth stage, as APAM residual levels increased once more, the supernatant grayscale decreased linearly, floc breakup became severe, and settling velocities neared stagnation. In the second stage, a correlation was noticed between higher APAM residual levels and better settling properties of coal slurry flocs. By studying residual dosage and energy input, guidance on how to optimize the sedimentation efficiency of the thickener and reduce dosage can be provided. [ABSTRACT FROM AUTHOR]