Search

Natural camouflage, seamlessly blending animals with their surroundings, remains challenging for artificial counterparts. Some animals exhibit near-permanent camouflaging, a product of decades of genetic evolution with their environment. At the same time, chameleons and octopuses achieve the ideal desired instantaneous camouflaging, unlike the heuristic-based approach of the artificial camouflage design. To attain similar perfection seen in animals, an evolutionary approach to artificial camouflage pattern development is necessary. Developing nations, primarily adopting the camouflage patterns of their more developed counterparts, may find themselves at a disadvantage. This study proposes a Genetic Algorithm (GA)-based approach to aid designers in developing countries in crafting effective camouflage. By parameterising heuristic development as a procedural texturing problem and evolving colour assignments iteratively, this approach aims to emulate the evolutionary process seen in nature. Using the K-means algorithm, genes are initialised based on background image colours, exploring factorial combinations to achieve optimal camouflage. With a maximum of 100 iterations and interactive feedback, the method addresses Nigeria's specific case and offers a faster development solution than developed nations' approaches. This evolutionary approach could revolutionise artificial camouflage development worldwide. [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]

Early skin cancer diagnosis saves lives as the disease can be successfully treated through complete excision. Computer-aided diagnosis methods are developed using artificial intelligence techniques to help earlier detection and identify hidden causes leading to cancers in skin lesion images. In skin cancer image classification problems, an ensemble of classifiers has demonstrated better classification ability than a single classification algorithm. Traditionally, training an ensemble uses the complete set of original features, where some of these features can be redundant or irrelevant and hence, may not provide useful information in generating good models for ensemble classification. Moreover, newly created features may help improve classification performance. To address this issue, the existing methods have used feature construction for building an ensemble classifier, which usually creates a fixed number of features that may fit the training data too well, resulting in poor test performance. This study develops a novel classification approach that combines ensemble learning, feature selection, and feature construction utilizing genetic programming (GP) to handle the above limitations. The proposed method automatically evolves variable-length feature vectors consisting of GP-selected and GP-constructed features suitable for training an ensemble classifier. This study evaluates the effectiveness of the proposed method on two benchmark real-world skin image datasets that include dermoscopy and standard camera images. The experimental results reveal that the proposed algorithm significantly outperforms four state-of-the-art convolutional neural network methods, the existing GP approaches, and 11 commonly used machine learning methods. Furthermore, this study also includes interpreting evolved individuals that highlight important skin cancer characteristics playing a vital role in discriminating images of different cancer classes. This study shows that high classification performance can be achieved at a low cost of computational resources and inference time, and accordingly, this method is potentially suitable to be implemented in mobile devices for the automated screening of skin lesions and many other malignancies in low-resource settings. [ABSTRACT FROM AUTHOR]

Purpose: Development of a color scheme representation to facilitate the interpretation of tri‐exponential DWI data from abdominal organs, where multi‐exponential behavior is more pronounced. Methods: Multi‐exponential analysis of DWI data provides information about the microstructure of the tissue under study. The tri‐exponential signal analysis generates numerous parameter images that are difficult to analyze individually. Summarized color images can simplify at‐a‐glance analysis. A color scheme was developed in which the slow, intermediate, and fast diffusion components were each assigned to a different red, green, and blue color channel. To improve the appearance of the image, histogram equalization, gamma correction, and white balance were used, and the processing parameters were adjusted. Examples of the resulting color maps of the diffusion fractions of healthy and pathological kidney and prostate are shown. Results: The color maps obtained by the presented method show the merged information of the slow, intermediate, and fast diffusion components in a single view. A differentiation of the different fractions becomes clearly visible. Fast diffusion regimes, such as in the renal hilus, can be clearly distinguished from slow fractions, such as in dense tumor tissue. Conclusion: Combining the diffusion information from tri‐exponential DWI analysis into a single color image allows for simplified interpretation of the diffusion fractions. In the future, such color images may provide additional information about the microstructural nature of the tissue under study. [ABSTRACT FROM AUTHOR]

This article introduces the possibility of studying graffiti using a colorimeter developed with Arduino hardware technology according to the Do It Yourself (DIY) philosophy. Through the obtained Red Green Blue (RGB) data it is intended to study and compare the information extracted from each of the graffiti present on different walls. The same color can be found in different parts of a single graffiti, but also in other graffiti that could a priori be of different authorship. Nevertheless, graffiti may be related, and it may be possible to group graffiti artists and "gangs" that work together. The methodology followed for the construction of the colorimeter and its real application in a practical case are described in four case studies. The case studies describe how graffiti were identified and recognized and they provide a comparison of the collected color samples. The results show the added value of the colorimeter in the graffiti recognition process, demonstrating its usefulness on a functional level. Finally, the contributions of this research are outlined, and an analysis is carried out of the changes to be made to the proposed method in the future, for improved graffiti color identification.

Retinal images play a pivotal contribution to the diagnosis of various ocular conditions by ophthalmologists. Extensive research was conducted to enable early detection and timely treatment using deep learning algorithms for retinal fundus images. Quick diagnosis and treatment planning can be facilitated by deep learning models' ability to process images rapidly and deliver outcomes instantly. Our research aims to provide a non-invasive method for early detection and timely eye disease treatment using a Convolutional Neural Network (CNN). We used a dataset Retinal Fundus Multi-disease Image Dataset (RFMiD), which contains various categories of fundus images representing different eye diseases, including Media Haze (MH), Optic Disc Cupping (ODC), Diabetic Retinopathy (DR), and healthy images (WNL). Several pre-processing techniques were applied to improve the model's performance, such as data augmentation, cropping, resizing, dataset splitting, converting images to arrays, and one-hot encoding. CNNs have extracted extract pertinent features from the input color fundus images. These extracted features are employed to make predictive diagnostic decisions. In this article three CNN models were used to perform experiments. The model's performance is assessed utilizing statistical metrics such as accuracy, F1 score, recall, and precision. Based on the results, the developed framework demonstrates promising performance with accuracy rates of up to 89.81% for validation and 88.72% for testing using 12-layer CNN after Data Augmentation. The accuracy rate obtained from 20-layer CNN is 90.34% for validation and 89.59% for testing with Augmented data. The accuracy obtained from 20-layer CNN is greater but this model shows overfitting. These accuracy rates suggested that the deep learning model has learned to distinguish between different eye disease categories and healthy images effectively. This study's contribution lies in providing a reliable and efficient diagnostic system for the simultaneous detection of multiple eye diseases through the analysis of color fundus images. [ABSTRACT FROM AUTHOR]

Color is one of the first criteria to assess the quality of cheese. However, very limited data are available on the color heterogeneity of the rind and its relationship with microbial community structure. In this study, the color of a wide range of smear-ripened Munster cheeses from various origins was monitored during storage by photographic imaging and data analysis in the CIELAB color space using luminance, chroma, and hue angle as descriptors. Different levels of inter- and intra-cheese heterogeneity were observed. The most heterogeneous Munster cheeses were the darkest with orange-red colors. The most homogeneous were the brightest with yellow-orange. K-means clustering revealed three clusters distinguished by their color heterogeneity. Color analysis coupled with metabarcoding showed that rinds with heterogeneous color exhibited higher microbial diversity associated with important changes in their microbial community structure during storage. In addition, intra-cheese community structure fluctuations were associated with heterogeneity in rind color. The species Glutamicibacter arilaitensis and Psychrobacter nivimaris/piscatorii were found to be positively associated with the presence of undesirable brown patches. This study highlights the close relationship between the heterogeneity of the cheese rind and its microbiota. [ABSTRACT FROM AUTHOR]

Emotion detection using features presented in the body has been comparatively understudied compared to other emotional modalities. This study investigated and compared how emotions are revealed through bodily sensations and body movement information. We propose a novel visualization method for addressing body part activation or deactivation associated with different emotions using motion capture data (bodily motion maps; BMMs) and aim to compare its emotional features with existing methods of addressing sensation towards body activation or deactivation using the computerised self-report method (bodily sensation maps; BSMs). A user study is conducted with twenty-nine participants to gather BSMs and BMMs under seven emotional statuses (happy, sad, surprise, angry, disgust, fearful, and neutral). The results indicate that people's BMMs as well as their BSMs contain shared features that can discriminate between emotions. The asynchronies between bodily sensation and body motion existed. Furthermore, convolutional neural network (CNN)-based automatic emotion recognition outperforms humans’ emotion recognition abilities. The implications of the current study's method of comparing emotional features between bodily sensation and body motion for future emotion-related studies for mental disorders are discussed. [ABSTRACT FROM AUTHOR]

Although facial expression recognition based on deep learning has become a major trend, existing methods have been found to prefer learning spurious statistical correlations and non-robust features during training. This degenerates the model's generalizability in practical situations. One of the research fields mitigating such misperception of correlations as causality is causal reasoning. In this article, we propose a learnable counterfactual attention mechanism, CA-FER, that uses causal reasoning to simultaneously optimize feature discrimination and diversity to mitigate spurious correlations in expression datasets. To the best of our knowledge, this is the first work to study the spurious correlations in facial expression recognition from a counterfactual attention perspective. Extensive experiments on a synthetic dataset and four public datasets demonstrate that our method outperforms previous methods, which shows the effectiveness and generalizability of our learnable counterfactual attention mechanism for the expression recognition task. [ABSTRACT FROM AUTHOR]

This article introduces the possibility of studying graffiti using a colorimeter developed with Arduino hardware technology according to the Do It Yourself (DIY) philosophy. Through the obtained Red Green Blue (RGB) data it is intended to study and compare the information extracted from each of the graffiti present on different walls. The same color can be found in different parts of a single graffiti, but also in other graffiti that could a priori be of different authorship. Nevertheless, graffiti may be related, and it may be possible to group graffiti artists and "gangs" that work together. The methodology followed for the construction of the colorimeter and its real application in a practical case are described in four case studies. The case studies describe how graffiti were identified and recognized and they provide a comparison of the collected color samples. The results show the added value of the colorimeter in the graffiti recognition process, demonstrating its usefulness on a functional level. Finally, the contributions of this research are outlined, and an analysis is carried out of the changes to be made to the proposed method in the future, for improved graffiti color identification. [ABSTRACT FROM AUTHOR]

This study addressed the need for a more accessible and efficient method of analyzing phenolic content in vegetable oils. The research aimed to develop a method that could be widely adopted by both researchers and industry professionals, ultimately revolutionizing the way phenolic content in vegetable oils is analyzed. This study developed a method of determining the total phenolic content (TPC) in vegetable oils using smartphone image analysis in the RGB color model. The method employed a gallic acid calibration solution and demonstrated exceptional determination coefficients for the RGB colors. The R—red color was selected as the basis for the analyses, and the method was statistically equivalent to standard UV/Vis spectrophotometry. The highest TPC was determined in hemp and olive oils, while the lowest was found in rice bran, grapeseed, and macadamia nut oils. This study concluded that smartphone image analysis, mainly using the R component of the RGB color model, was a superior alternative to traditional spectrophotometric methods for determining the TPC in vegetable oils. This innovative approach could revolutionize phenolic content analysis by providing researchers and industry professionals with a cost-effective, safe, and efficient tool. The estimated limit of detection (LOD) of 1.254 mg L−1 and limit of quantification (LOQ) of 3.801 mg L−1 further confirmed the reliability and comparability of the method. With these findings, it was expected that the method would be widely adopted in the future. [ABSTRACT FROM AUTHOR]

Purpose: The presence of alcoholic stool in biliary atresia (BA) patients is the basis of a stool color card (SCC), a screening tool that has led to more patients receiving Kasai portoenterostomy earlier. This study aimed to evaluate the color image processing of stool images captured using smartphones. We propose that measuring digital color parameters is a more objective method for identifying BA stools and may improve the sensitivity of BA screening. Methods: A prospective study was conducted in five hospitals in Thailand between October 1, 2020, and December 31, 2021. Stools from infants presenting with jaundice, acholic stool, or dark-colored urine were photographed. Digital image color analysis was performed, and software was developed based on the color on the original SCC. Sensitivity and specificity for predicting BA stools were compared between the SCC and the software. Results: Of 33 infants eligible for data collection, 19 were diagnosed with BA. Saturation and blue were two potential digital color parameters used to differentiate BA stools. The receiver operating characteristic curve was used to determine the optimum cutoff point of both values, and when saturation =56 or blue =61 was set as a threshold for detecting BA stool, high accuracy was achieved at 81.8% and 78.8%, respectively. Conclusion: Digital image processing is a promising technology. With appropriate cutoff values of saturation in hue, saturation, value and blue in red, green, blue color models, BA stools can be identified, and equivocal-colored stools of non-BA patients can be differentiated with acceptable accuracy in infants presenting with jaundice. [ABSTRACT FROM AUTHOR]

Approaches for remote sensing can be used to estimate the influence of changes in environmental conditions on terrestrial plants, providing timely protection of their growth, development, and productivity. Different optical methods, including the informative multispectral and hyperspectral imaging of reflected light, can be used for plant remote sensing; however, multispectral and hyperspectral cameras are technically complex and have a high cost. RGB imaging based on the analysis of color images of plants is definitely simpler and more accessible, but using this tool for remote sensing plant characteristics under changeable environmental conditions requires the development of methods to increase its informativity. Our review focused on using RGB imaging for remote sensing the characteristics of terrestrial plants. In this review, we considered different color models, methods of exclusion of background in color images of plant canopies, and various color indices and their relations to characteristics of plants, using regression models, texture analysis, and machine learning for the estimation of these characteristics based on color images, and some approaches to provide transformation of simple color images to hyperspectral and multispectral images. As a whole, our review shows that RGB imaging can be an effective tool for estimating plant characteristics; however, further development of methods to analyze color images of plants is necessary. [ABSTRACT FROM AUTHOR]

This study presents an innovative method utilizing smartphone for automated progress monitoring at underground pipe installation sites. Leveraging the LiDAR iPhone camera, the method captures detailed point cloud data of construction sites. Sophisticated color analysis of images accurately distinguishes between areas with and without pipes within excavations. Key aspects of the proposed workflow include segmentation of the excavation area, differentiation between main and side excavations, and application of an earth color mask in the RGB space to isolate pipes. The research focuses on enhancing measurement precision for excavation width, depth, and pipe burial depth, significantly reducing the manual labor traditionally required at construction sites, thereby offering an efficient and cost-effective solution. We further demonstrated the robustness of the proposed algorithm by applying it to two types of data acquired at actual construction sites. This approach is expected to contribute significantly to the digital transformation in the construction industry.

Modern technology in the field of images led to the issue of information transfer speed. As a result, there was need to find new and rapid technology in application to reach good results. In this paper, we propose new transformations derived from Laguerre polynomials. The image is analyzed using new wavelets to remove the noise from the color image and to avoid the problem of large data and the difficulty of transferring this data to keep it from being lost. The image is compressed to reduce the space occupied by this huge data with the help of the MATLAB program. The obtained results show the efficiency of our proposed method. [ABSTRACT FROM AUTHOR]

Underwater imaging is often affected by light attenuation and scattering in water, leading to degraded visual quality, such as color distortion, reduced contrast, and noise. Existing underwater image enhancement (UIE) methods often lack generalization capabilities, making them unable to adapt to various underwater images captured in different aquatic environments and lighting conditions. To address these challenges, a UIE method based on the conditional denoising diffusion probabilistic model (DDPM) is proposed (DiffWater), which leverages the advantages of DDPM and trains a stable and well-converged model capable of generating high-quality and diverse samples. Considering the multiple distortion issues in underwater imaging, unconditional DDPM may not achieve satisfactory enhancement and restoration results. Therefore, DiffWater utilizes the degraded underwater image with added color compensation as a conditional guide, through which the DiffWater achieves high-quality restoration of degraded underwater images. Particularly, the proposed DiffWater introduces a color compensation method that performs channelwise color compensation in the RGB color space, tailored to different water conditions and lighting scenarios, and utilizes this condition to guide the denoising process. In the experimental section, the proposed DiffWater method is tested on four real underwater image datasets and compared against existing methods. Experimental results demonstrate that DiffWater outperforms existing comparison methods in terms of enhancement quality and effectiveness, exhibiting stronger generalization capabilities and robustness. [ABSTRACT FROM AUTHOR]

Heterogeneous pedestrian images are captured by visible and infrared cameras with different spectrums, which play an important role in night-time video surveillance. However, visible infrared person re-identification (VI-REID) is still a challenging problem due to the considerable cross-modality discrepancies. To extract modality-invariant features which are discriminative for the person identity, recent studies are inclined to regard modality-specific features as noise and discard them. Actually, the modality-specific characteristics containing background and color information are indispensable for learning modality-shared features. In this paper, we propose a novel Dual-Adversarial Representation Disentanglement (DARD) model to separate modality-specific features from tangled pedestrian representations and effectively learn the robust modality-invariant representations. Specifically, our method employs dual-adversarial learning, incorporating image-level channel exchange and feature-level magnitude change to introduce variations in modality-specific representations. This deliberate perturbation raises the learning difficulty for the model to learn modality-shared features. Simultaneously, to control the changing scope of modality-specific features, bi-constrained noise alleviation is introduced during adversarial learning, keeping the balance of feature generation and adversary. The proposed dual-adversarial learning methodology enhances the robustness against cross-modality visual discrepancy and strengthens the discriminative power of the learned modality-shared representations without introducing additional network parameters. This improvement further elevates the retrieval performance of VI-REID. Extensive experiments with insightful analysis on two cross-modality re-identification datasets verify the effectiveness and superiority of the proposed DARD method. [ABSTRACT FROM AUTHOR]

Despite being a valuable meat resource, Japanese Black delivered cows suffer from the problem of yellowing fat color. This study aimed to investigate the effects of the parity and the fattening period on the fat color in Japanese Black delivered cows using image analysis technology. Data from 504 delivered cows that were fattened for 365 days or less at the last farmers and shipped to the carcass market in Hokkaido between September 2016 and July 2022 were analyzed. L*a*b* values were determined through image analysis for subcutaneous and intermuscular fat in three locations of the 6th-7th rib cross-section. Correlation coefficients were calculated to determine the relationship among Beef Fat Standard (BFS) No. and each trait, and the b* value of subcutaneous fat was found to have the highest correlation coefficient (r = 0.76, P < 0.01). The parity and the fattening period had a significant effect on BFS No., the b* value of subcutaneous fat, the b* value of intermuscular fat surrounded by M.spinalis, M.semispinalis capitis and M.longissimus thoracis, and the average b* value of color difference between subcutaneous fat and intermuscular fat (P<0.05). At 4 months of the fattening period, BFS No. was 5.4, which decreased to 4.2 at 5 months of the fattening period (P < 0.01). Similarly, the b* value of subcutaneous fat decreased from 21.2 at 4 months of the fattening period to 14.2 at 5 months of the fattening period (P < 0.01). The average b* value of color difference between subcutaneous fat and intermuscular fat decreased significantly at 5 months of the fatting period(P < 0.01). This study confirmed that when grading of BFS No., the color of subcutaneous fat tends to be the determining factor. The results indicated that parity and the length of the fattening period significantly affect fat color, which is yellowish until 4 months of the fattening period. Moreover, the study found that BFS No. decreased signifi- cantly after the fattening period longer than 5 months. [ABSTRACT FROM AUTHOR]

Sour cherries are a perishable raw material, and their preservation is needed to extend their availability to consumers. Improving drying techniques is desirable to ensure the highest quality of products. This study aimed to determine image textures from color channels R, G, B, L, a, b, X, Y, and Z; color parameters L*, a*, and b*; the color difference (ΔE) of raw materials and dried fruit; and the sensory attributes of dried sour cherry products prepared using an innovative approach. Three sour cherry cultivars, 'Nefris', 'Debreceni Botermo', and 'Łutówka', were used in the experiment. Sour cherries were subjected to freezing and pit removal before drying. The simultaneous osmotic–microwave–vacuum drying was carried out in one process lasting an hour and combining osmotic dehydration using a 40 °Bx sucrose solution and microwave–vacuum drying at microwave powers of 100 W for 900 s, 300 W for 900 s, 250 W for 900 s, and 0 W for stabilization for 900 s and a pressure of 30 ± 2 hPa. After drying, the quality assessment of products was performed using non-destructive image analysis and color measurements, as well as sensory analysis, including non-destructively and destructively assessed attributes. The highest changes in textures occurred for the GHMean (histogram's mean for color channel G) (from 30.69 to 22.64) and LHMean (histogram's mean for color channel L) (from 66.93 to 59.07) of images of the cultivar 'Łutówka', and the smallest changes were found for the cultivar 'Nefris'. Drying had a statistically significant effect on the color parameters of the 'Debreceni Botermo' and 'Łutówka' sour cherries. The value of ΔE was the highest (10.44) for 'Debreceni Botermo' and the smallest (1.98) for 'Nefris'. All cultivars of dried sour cherries had very high values of overall quality, reaching 8.9 for 'Nefris' and 'Debreceni Botermo' and 8.8 for 'Łutówka'. The 'Nefris' sour cherry was characterized by the highest value of flavor of 9.0. All dried samples were attractive in terms of their external appearance. The sensory parameters related to taste, texture, and crunchiness were also satisfactory. Innovative simultaneous osmotic–microwave–vacuum drying allowed for the obtainment of dried sour cherries with a high quality, including acceptable sensory attributes. [ABSTRACT FROM AUTHOR]

This paper presents a physical space design method for mixed reality-based immersive environments by improving the color rendering of optically visible head-mounted displays. In OST-HMD, the phenomenon that the light of the external environment is combined with the enhanced image occurs, which reduces the visibility of the content. Moreover, previous studies to solve this problem required additional optical components or performed only simple verification. Proposed physical space was designed using black curtains, blinds, low-reflection structures, and adjustable lighting. The physical space can be adapted to the intended use of the physical space through physical transitions for multiple users without additional optics. To verify the usefulness of this environment, we measured the color gamut and intensity spectrum in three experimental environments. Also, we analyzed the factors that change the color gamut according to the components and the surrounding environment. As a result, the color gamut improved by up to 4.7 times from 19.92% to 93.53% based on the environment and improved by up to 4.1 times from 21% to 86.29% depending on the location. The experimental results revealed that the presented method could reduce the factors that degrade the color gamut within all measurement locations and significantly improve the color gamut. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Southeast University (English Edition) is the property of Journal of Southeast University Editorial Office 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.)

This study addresses the critical issue of land subsidence in densely populated agriculture-based country, Bangladesh, focusing on the Barapukuria coal mine area. Our research employed time-series analysis of Landsat satellite imagery from 2005 to 2020, coupled with vertical electrical sounding resistivity methods. Through the false color composite image analysis in Earth Engine and GIS-based mapping, we quantified the areal extent of subsidence, and results were validated by field visits and cross-referencing with ESRI and dynamic world land use–land cover maps. Our study revealed a concerning trend of subsidence moving from west to east, towards the two nearby residential areas. Most importantly, the rate of areal extent of subsidence was alarming (17.4 acres per year), resulting in a cumulative loss of 205 acres since 2008. Linear regression predicts that this subsided area will double to around 405 acres by 2030, indicating significant risk to nearby communities. The trajectory of subsidence extent led us to examine the subsurface condition of nearby villages using calibrated vertical electrical sounding and borehole data. This revealed a higher resistivity in the northern area, indicating a future subsidence risk compared to the southern part. This was further confirmed by subsurface lithology, composed mainly of Holocene deposits containing clay, clayey sand, and sand. These layers, with their inherent instability and higher consolidation potential, exhibited higher resistivity and more prone to land subsidence. Overall, this study provides valuable insights for predicting subsidence, assessing associated risks, and guiding policy decisions to prevent future damage and facilitate community rehabilitation. [ABSTRACT FROM AUTHOR]

This paper presents a physical space design method for mixed reality-based immersive environments by improving the color rendering of optically visible head-mounted displays. In OST-HMD, the phenomenon that the light of the external environment is combined with the enhanced image occurs, which reduces the visibility of the content. Moreover, previous studies to solve this problem required additional optical components or performed only simple verification. Proposed physical space was designed using black curtains, blinds, low-reflection structures, and adjustable lighting. The physical space can be adapted to the intended use of the physical space through physical transitions for multiple users without additional optics. To verify the usefulness of this environment, we measured the color gamut and intensity spectrum in three experimental environments. Also, we analyzed the factors that change the color gamut according to the components and the surrounding environment. As a result, the color gamut improved by up to 4.7 times from 19.92% to 93.53% based on the environment and improved by up to 4.1 times from 21% to 86.29% depending on the location. The experimental results revealed that the presented method could reduce the factors that degrade the color gamut within all measurement locations and significantly improve the color gamut.

Sensor-based ore sorting is a technology used to classify high-grade mineralized rocks from low-grade waste rocks to reduce operation costs. Many ore-sorting algorithms using color images have been proposed in the past, but only some validate their results using mineral grades or optimize the algorithms to classify rocks in real-time. This paper presents an ore-sorting algorithm based on image processing and machine learning that is able to classify rocks from a gold and silver mine based on their grade. The algorithm is composed of four main stages: (1) image segmentation and partition, (2) color and texture feature extraction, (3) sub-image classification using neural networks, and (4) a voting system to determine the overall class of the rock. The algorithm was trained using images of rocks that a geologist manually classified according to their mineral content and then was validated using a different set of rocks analyzed in a laboratory to determine their gold and silver grades. The proposed method achieved a Matthews correlation coefficient of 0.961 points, higher than other classification algorithms based on support vector machines and convolutional neural networks, and a processing time under 44 ms, promising for real-time ore sorting applications.

Hydrocarbon contamination in the environment poses a significant challenge, and various control methods have been explored. Soil remediation by flotation has been proposed as an effective approach. This method involves the separation of hydrophobic compounds, such as soil hydrocarbons, by introducing air into a stirred reactor containing the soil pulp designated for remediation. Experiments were conducted using a 5 L Batch flotation cell to evaluate operating conditions. These experiments focused on obtaining flotation kinetics with different organic mixtures, including fine sands measuring under 150 µm. The experimental design encompassed airflow, hydrocarbon concentration, and surfactant dosage. The research utilized a diluted pulp (3% solids) with a high organic concentration (8 and 17 g/L). Flotation kinetics were measured by developing an innovative technique based on pulp color and image processing software. This technique facilitated the tracking of concentration changes over time under Beer-Lambert's Law. Subsequently, the results were adjusted using kinetic models commonly employed in mineral flotation, including the first-order, Kelsall, and Klimpel models. This comprehensive analysis sought to elucidate the underlying phenomenology and assess the potential for industrial-scale implementation. The laboratory findings indicate the possibility of achieving recoveries of up to 87%, with a first-order kinetic constant of 0.7 (1/min). Both the gas flow rate and the addition of surfactant exert substantial influence on this constant, consistent with the observed phenomenology of this study. This study explores the integration of image analysis in flotation for hydrocarbon-contaminated soil remediation. The research aims to optimize remediation strategies by examining variables such as Beer-Lambert's law and prevalent kinetic models. The study focuses on scalable, eco-friendly decontamination methods, emphasizing enhanced process control and comprehension within soil flotation systems. [ABSTRACT FROM AUTHOR]

We propose a deep learning-based reference comparison system based on a twin network (also known as a Siamese network) for high-performance inspection of integrated circuit (IC) substrates. However, reference comparison-based inspection methods may suffer from false positives when inspecting image pairs with variations, such as mis-registration and color changes. To address these problems, we also propose a novel co-attention module that jointly considers the spatial-wise and channel-wise correlations between a feature block in one image and all other feature blocks in the other image to find similar feature blocks in the other image. By comparing the feature block in one image with similar feature blocks in the other image, the module can reduce the differences in areas where registration errors and/or color variation exist, thereby making the proposed inspection method more robust to image variation than existing methods. We verified the usefulness of the proposed method through experiments using an IC substrate dataset. In the experiments, the proposed method achieved significantly improved performance compared with existing methods in terms of precision and f1-score when the recall is almost the same. [ABSTRACT FROM AUTHOR]

Spectral investigation of the canopy has an increasing importance in precision viticulture to monitor the effect of biotic and abiotic stress factors. In this study, RGB (color model, red, green, blue)-based vegetation indices were evaluated to find a correlation with grapevine leaf chlorophyll concentration. 'Hárslevelű' (Vitis vinifera L.) leaf samples were obtained from a commercial vineyard and digitalized. The chlorophyll concentration of the samples was determined with a portable chlorophyll meter. Image processing and color analyses were performed to determine the RGB average values of the digitized samples. According to the RGB values, 31 vegetation indices were calculated and evaluated with a correlation test and multivariate regression. The Pearson correlation between the chlorophyll concentration and most of the indices was significant (p < 0.01), with some exceptions. The same results were obtained with the Spearman correlation as the relationship had high significance (p < 0.01) for most of the indices. The highest Pearson correlation was obtained with the index PCA2 (Principal Component Analysis 2), while Spearman correlation was the highest for RMB (difference between red and blue) and GMB (difference between green and blue). The multivariate regression model also showed a high correlation with the pigmentation. We consider that our results would be applicable in the future to receive information about the canopy physiological status monitored with on-the-go sensors. [ABSTRACT FROM AUTHOR]

Image white-balancing is an integral part of every camera's processing pipeline. White-balancing is used to remove illumination chromaticity from an image. Most research in this field has been limited to images with a single uniform illuminant. In this paper, we introduce a novel method for illumination estimation for situations where the scene is illuminated by a variable number of different illuminants and where the illumination in the scene can be non-uniform. The proposed method uses a lightweight convolutional neural network that achieves state-of-the-art results. The method performs illumination estimation on a patch-by-patch basis. We use the assumption that only one illuminant affects each patch since they are so small. Unlike other such methods, our method uses features extracted from the entire image to perform patch illumination estimation. The paper also shows how the image features improve method accuracy with a minimal increase in complexity. The proposed method has around 42 k parameters, and it was tested on three different cameras from the Large-Scale Multi-Illuminant dataset. [ABSTRACT FROM AUTHOR]

Copyright of Al-Mustansiriyah Journal of Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) 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.)

Multigrid (MG) methods are among the best choice for stable and efficient 3D forward modeling of electromagnetic (EM) fields over large area due to their linear dependence of computational time on grid size. However, as the frequency decreases to near zero and/or the grid is increasingly stretched, MG solvers for EM modeling based on the curl-curl equations converge slowly or even diverge. In this letter, we develop an efficient MG algorithm combined with a two-color plane Gauss-Seidel (GS) smoother for finite difference forward modeling of EM fields particularly at low frequencies. In this algorithm, we group different planes of the grid nodes into two colors. In each color, the components attached to different planes are totally decoupled and can be solved simultaneously, which can be distributed to different processors. The Dublin Test Model 1 is used to verify the accuracy of our algorithm and examine the numerical performance of our method against MG algorithms based on a four-color cell-block GS smoother and the Bi-Conjugate Gradient stabilized (BICGstab) smoother (as four-color cell-block GS MG and BICGstab-MG, respectively), and BICGstab and Quasi-Minimal Residual (QMR) both preconditioned with block incomplete lower-upper (blockILU) decomposition (as blockILU-BICGstab and blockILU-QMR, respectively). The numerical test based on OpenMP shows the good parallelization of our algorithm. Grids stretched to different degrees are designed to examine its ability to handle grid-stretching. The numerical performance comparison indicates its remarkable dominance in efficiency and stability. [ABSTRACT FROM AUTHOR]

Autonomous underwater vehicles (AUVs) based on remote-sensing technology have been widely applied in various underwater tasks. However, the complex underwater environment leads to challenges such as color distortion, blurred details, and fog effects in the underwater image directly acquired by AUVs. Although numerous existing methods aim to remove the color cast and restore image details, their effectiveness is still limited. This letter proposes a new method based on a deformable convolutional network and constrained by contrastive learning for underwater image enhancement. First, we propose a deformable convolutional residual block (DCRB) to achieve a more precise restoration of texture details by adaptively adjusting the convolution kernel shape. At the same time, we utilize the long-skip connection method of the U-Net architecture to preserve information that is prone to loss in shallow networks. Second, we propose a color contrastive loss function to compare the color difference between distorted images and the ground truth, resulting in a more realistic enhanced image. Finally, experimental results demonstrate that the proposed method outperforms the state-of-the-art methods regarding image quality and visual appeal. [ABSTRACT FROM AUTHOR]

This letter proposes an effective underwater image restoration method that consists of a local image descattering and an adaptive brightness improvement. First, we establish an adaptive objective function for improving the brightness of underwater image according to the best-preserved channel of an image, and an augmented Lagrange multiplier-based alternating direction minimization algorithm is derived to solve the optimization problem. Second, we introduce a local transmission estimation method that takes into account the different attenuation of light on the red, green, and blue channels, which overcomes the limitation that existing methods heavily depend on global transmission over the entire image. Extensive experiments on real-world underwater images demonstrate the effectiveness of the proposed method in underwater image restoration. Moreover, our method shows good generalization capability for enhancing remote sensing and nighttime images. [ABSTRACT FROM AUTHOR]

In remote sensing, plenty of multispectral images are publicly available from various landcover satellite missions. Contrastive self-supervised learning is commonly applied to unlabeled data but relies on domain-specific transformations used for learning. When focusing on vegetation, standard transformations from image processing cannot be applied to the near-infrared (NIR) channel, which carries valuable information about the vegetation state. Therefore, we use contrastive learning, relying on different views of unlabeled, multispectral images to obtain a pretrained model to improve the accuracy scores on small-sized remote sensing datasets. This study presents the generation of additional views tailored to remote sensing images using atmospheric correction as an alternative transformation to color jittering. The purpose of the atmospheric transformation is to provide a physically consistent transformation. The proposed transformation can be easily integrated with multiple channels to exploit spectral signatures of objects. Our approach can be applied to other remote sensing tasks. Using this transformation leads to improved classification accuracy of up to 6%. [ABSTRACT FROM AUTHOR]

Seamline detection is one of the most important issues in mosaicking high-resolution remote sensing images (HRRSIs). However, it is difficult to make a balance between efficiency and accuracy. On that account, a shortest matrix path-based dynamic programming (SMP-DP) algorithm is proposed to find the optimal seamline for HRRSI mosaicking. First, a pixel cost matrix defined by intensity difference, gradient similarity, and geometric difference is constructed in the overlapping area. Second, the least average path cost from the starting pixel to each pixel is calculated and the SMP-DP algorithm is applied to find the optimal path. Experimental results on HRRSI prove that the proposed method detects high-quality seamline and crosses much fewer objects with the highest computational efficiency, compared with the state-of-the-art method and commercial software. [ABSTRACT FROM AUTHOR]

Spectral indices are a well-established remote sensing tool showcased in many studies pertaining to fields such as agriculture, forest ecology, geology, soil sciences, vegetation, water resources, and urban development. In the case of geology, several indices already exist for the purpose of highlighting regions with interesting lithologies, such as iron oxides, aluminous clays, carbonates, and mafic to ultramafic minerals, based on signature absorption features in their reflectance spectra. However, in the literature, most indices often depend on the few, wide spectral bands used by spaceborne multispectral imagers such as Landsat 8 OLI, Terra ASTER, and Sentinel-2 MSI. Hyperspectral imagers are able to glean more detailed compositional information about a rock surface by operating with a myriad of narrow spectral bands, though the usage of these bands in spectral indices for mining and exploration purposes remains largely unexplored. We propose a new bastnäsite index (BI) capable of detecting the presence of rare earth elements (REEs) and mapping their relative abundances across rock surfaces. Using four reference bands and four absorption bands in the visible to near-infrared wavelength range, we apply this novel technique in a laboratory setting to ore samples extracted from the carbonatite body localized in the Sulfide Queen mine in Mountain Pass, CA, USA. Visual inspection is used to compare an index map to corresponding reflectance spectra for areas of known high and low REE abundances, demonstrating its potential as a fast and straightforward means to assess REE ore grade remotely. [ABSTRACT FROM AUTHOR]

This study investigated the relationship between "rust color distribution ratio," "corrosion surface shape," and "fatigue strength" of high-strength galvanized steel wires used in cable supported bridges. The study utilized a digital image color analysis system to classify the rust color distribution rate and categorize corrosion levels based on the distribution ratio. The relationship between cross-sectional loss rate and corrosion depth tendency was visually and quantitatively comprehended from the categorized corrosion levels. The study found that fatigue and tensile strengths of the specimens from the corrosion levels set in this study were equivalent to or higher than those of new wires. However, the possibility of variations due to the small number of specimens or insufficient corrosion progress cannot be ruled out. [ABSTRACT FROM AUTHOR]

Copyright of Journal of the American Institute for Conservation is the property of Taylor & Francis Ltd 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.)

Color in artworks is an inspirational source for fashion designers. Product color is a fundamental design element to stimulate customers' emotional response as designers intend or express conceptual trends they want to infuse into products. Thus, artwork color analysis and the color selection process are crucial for product designs. This study aims to establish digital color analysis whereby fashion designers can extract colors from digital images of artworks and find relevant fashion codes with automation. The analysis method provides the image color attributes in Munsell, Practical Color Coordinate System, and Shigenobu Kobayashi Color Scale. It reveals underlying color semiotics representative of digital images. That is essential to provide color guidance to fashion experts when planning product colors. The semiotics analysis is based on Kobayashi's 3-color combination scale and quantitatively estimates the similarity of an artwork image to the 3-color bar. Symbolic adjective of the image is found whereby image coordinates in semantic space can be estimated. This method was used to investigate the colors of 190 Monet's paintings. The results found that Monet frequently expressed subject matters in nature with colors of low saturation tone. We explore the manifestation of the painting colors in dress collections as fashion codes. This approach found that an inspiring painting and a designed dress impress the same or similar fashion codes. [ABSTRACT FROM AUTHOR]

Classifying pixels according to color, and segmenting the respective areas, are necessary steps in any computer vision task that involves color images. The gap between human color perception, linguistic color terminology, and digital representation are the main challenges for developing methods that properly classify pixels based on color. To address these challenges, we propose a novel method combining geometric analysis, color theory, fuzzy color theory, and multi-label systems for the automatic classification of pixels into 12 conventional color categories, and the subsequent accurate description of each of the detected colors. This method presents a robust, unsupervised, and unbiased strategy for color naming, based on statistics and color theory. The proposed model, "ABANICCO" (AB ANgular Illustrative Classification of COlor), was evaluated through different experiments: its color detection, classification, and naming performance were assessed against the standardized ISCC–NBS color system; its usefulness for image segmentation was tested against state-of-the-art methods. This empirical evaluation provided evidence of ABANICCO's accuracy in color analysis, showing how our proposed model offers a standardized, reliable, and understandable alternative for color naming that is recognizable by both humans and machines. Hence, ABANICCO can serve as a foundation for successfully addressing a myriad of challenges in various areas of computer vision, such as region characterization, histopathology analysis, fire detection, product quality prediction, object description, and hyperspectral imaging. [ABSTRACT FROM AUTHOR]