Search

• Understanding plastic litter in cities is crucial to preventing marine pollution. • Citizen science is suitable for long-term, extensive data collection. • Despite human error, ∼30 % of data could be used to visualize and quantify litter. • Litter in cities was studied using Pirika and deep learning-based image processing. • Trained models exhibited high precision and recall in classifying litter types. Cities are a major source of litter pollution. Determination of the abundance and composition of plastic litter in cities is imperative for effective pollution management, environmental protection, and sustainable urban development. Therefore, here, a multidisciplinary approach to quantify and classify the abundance of litter in urban environments is proposed. In the present study, litter data collection was integrated via the Pirika smartphone application and conducted image analysis based on deep learning. Pirika was launched in May 2018 and, to date, has collected approximately one million images. Visual classification revealed that the most common types of litter were cans, plastic bags, plastic bottles, cigarette butts, cigarette boxes, and sanitary masks, in that order. The top six categories accounted for approximately 80 % of the total, whereas the top three categories accounted for more than 60 % of the total imaged litter. A deep-learning image processing algorithm was developed to automatically identify the top six litter categories. Both precision and recall derived from the model were higher than 75 %, enabling proper litter categorization. The quantity of litter derived from automated image processing was also plotted on a map using location data acquired concurrently with the images by the smartphone application. Conclusively, this study demonstrates that citizen science supported by smartphone applications and deep learning-based image processing can enable the visualization, quantification, and characterization of street litter in cities. [ABSTRACT FROM AUTHOR]

Urban public safety management relies heavily on video surveillance systems, which provide crucial visual data for resolving a wide range of incidents and controlling unlawful activities. Traditional methods for target detection predominantly employ a two-stage approach, focusing on precision in identifying objects such as pedestrians and vehicles. These objects, typically sparse in large-scale, lower-quality surveillance footage, induce considerable redundant computation during the initial processing stage. This redundancy constrains real-time detection capabilities and escalates processing costs. Furthermore, transmitting raw images and videos laden with superfluous information to centralized back-end systems significantly burdens network communications and fails to capitalize on the computational resources available at diverse surveillance nodes. This study introduces DiffRank, a novel preprocessing method for fixed-angle video imagery in urban surveillance. The method strategically generates candidate regions during preprocessing, thereby reducing redundant object detection and improving the efficiency of the detection algorithm. Drawing upon change detection principles, a background feature learning approach utilizing shallow features has been developed. This approach prioritizes learning the characteristics of fixed-area backgrounds over direct background identification. As a result, alterations in ROI are efficiently discerned using computationally efficient shallow features, markedly accelerating the generation of proposed Regions of Interest (ROIs) and diminishing the computational demands for subsequent object detection and classification. Comparative analysis on various public and private datasets illustrates that DiffRank, while maintaining high accuracy, substantially outperforms existing baselines in terms of speed, particularly with larger image sizes (e.g., an improvement exceeding 300 % at 1920×1080 resolution). Moreover, the method demonstrates enhanced robustness compared to baseline methods, efficiently disregarding static targets like mannequins in display windows. The advancements in candidate area preprocessing enable a balanced approach between detection accuracy and overall detection speed, making the algorithm highly applicable for real-time on-site analysis in edge computing scenarios and cloud-edge collaborative computing environments. [ABSTRACT FROM AUTHOR]

Reversible solid oxide cells (r -SOCs) are regarded as a solution form of clean energy generation towards a green hydrogen energy transition. However, during transportation, installation, and operation, they are required to withstand dynamic conditions as they face thermal, mechanical, and vibrational effects. Assessing the interplay of the thermomechanical and dynamical impacts on r-SOC materials during the mode-switch from electrolysis to fuel cell operation is the subject of this current comprehensive study. Advanced FEM-based homogenisation techniques have been harnessed in predicting and evaluating the detailed transients during static and dynamic loading. The intricate 3D thermal profiles throughout the transient reversible dual-modus operation from a typical r-SOC study have been derived using advanced image processing. Orthotropic material properties were incorporated into a unified macroscopic scale model by deriving the complex 3D microstructure geometry characteristics of the cell materials and component layers. The comprehensive thermomechanical and pre-stressed modal analysis results showed that the static and dynamic forces in fuel cell mode are more pronounced, whereas, in electrolysis operation, the dynamical behaviour highly depends on geometrical and operating conditions. Smaller component size shows higher natural frequencies and more intense vibration, leading to higher deformation attributed to complex mode shapes and reduced flexural rigidity. These insights are essential for optimizing r-SOC design parameters, enhancing their dynamic and structural reliability throughout their dual-mode operation lifespan. • Influence of cell size and thickness on static and dynamic r-SOC behaviour. • 3D physical r-SOC microstructure model generation and virtually characterisation. • Thermal field derivation using data recognition and image processing techniques. • 3D thermomechanical stresses, natural frequencies, and mode shapes are determined. • Comparison of thermomechanical and dynamic effects on reversible operation. [ABSTRACT FROM AUTHOR]

Generation of hidden attractor with complicated phase portrait in chaotic system with no equilibrium has presented a new research focus in the past decade. However, the existing approaches usually follow the rule that you reap what you sow, i.e., taking an no-equilibrium chaotic system as the seed. In this paper, a novel approach to the generation of no-equilibrium multi-fold hidden attractors is presented. The offset boosting and the operation of complex number are applied to several cases, including the seed chaotic systems with no equilibrium, with single unstable node, or with single stable node-focus. In specific, the offset boosting shifts the single non-zero equilibrium to the origin, then the operation of complex number rules out the equilibrium in the folded system and generates multi-fold trajectories. The highlight is that the proposed approach is not limited to the no-equilibrium seed system, but also applicable for different types of single-equilibrium seed systems, even the seed system with a single line of equilibrium. The detailed numerical simulations and experiments confirmed the feasibility of the proposed approach. Finally, an image encryption algorithm and its practical microcontroller-based implementation are presented to support the potential application. • Systematic approach for folding trajectory of chaotic system. • New multi-fold chaotic hidden attractors with no equilibrium. • New chaos-based encryption algorithm for image security. • Dynamic memory scheme for microcontroller implementation. [ABSTRACT FROM AUTHOR]

Detecting the shoreline is an important task for its potential use. The shoreline allows cropping of the image into two separate areas that present the water area and the shore. It is particularly interesting because the images can be used to analyze pollution, land development, or even waterfront erosion. Unfortunately, automatic shoreline detection is a complex problem due to numerous physical and atmospheric issues. In this paper, we present a solution based on a U-net convolutional network, that is trained to shoreline detection on a dedicated database. The database is automatically generated by applying image processing techniques and a heuristic algorithm. Using heuristics, optimal values of mask generation parameters are determined. Consequently, the solution allows for the automation of generating a set of masks by analyzing the boundary line and the efficiency of the segmentation network. The proposed solution allows for the analysis of the coastline, where potential obstacles and even occurring waves can be quickly detected. To evaluate the proposed solution, tests were carried out in real conditions, which showed the effectiveness of the model. In addition, tests were carried out on a publicly available database, which allowed for obtaining higher results than existing methods. [ABSTRACT FROM AUTHOR]

Solving tensor systems is a common task in scientific computing and artificial intelligence. In this paper, we propose a tensor randomized average Kaczmarz method with adaptive parameters that exponentially converges to the unique least Frobenius norm solution of a given consistent tensor system under the t-product structure. In order to accelerate convergence, a tensor average Kaczmarz method based on stochastic heavy ball momentum technique (tAKSHBM) is proposed. The tAKSHBM method utilizes iterative information to update parameters instead of relying on prior information, addressing the problem in the adaptive learning of parameters. Additionally, the tAKSHBM method based on Fourier transform is proposed, which can be effectively implemented in a distributed environment. It is proven that the iteration sequences generated by all the proposed methods are convergent for given consistent tensor systems. Finally, we conduct experiments on both synthetic data and practical applications to support our theoretical results and demonstrate the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

An inspection in tablet appearance integrity before bottling is regarded as a routine task in a pharmaceutical factory. Although some methods such as automated optical instrument, video or artificial intelligence (AI) are currently available in industry, it usually pays for a complex computational process as well as high cost. Based on the symmetry of tablet appearance in reality, this study develops a biaxial scanning slope symmetry algorithm to realize a dynamic real-time tablet defect detection with a simple arithmetic operation. First, the tablet is discretely scanned using image sensor in two axes, i.e. X and Y directions, simultaneously. Second, the analogy output signals generated from the sensor during the scanning process is discretely digitized and stored in an array. Third, the coordinate of center point in the series data array is identified from every line scanning. Fourth, every section slope between two nearby center points from the first to last lines is formulated and calculated sequentially. Finally, the square mean error (SME) is used to evaluate the shape defect situation according to all accumulated errors from every slope variation. The experimental results verify that the proposed algorithm can achieve both fast and accurate detection performance. [ABSTRACT FROM AUTHOR]

Poisson image deblurring, which aims to restore the latent image from its blurred and noisy observation, has drawn significant attention in image processing. Due to its ill-posed nature, enhancing image quality often involves incorporating a well-defined prior to effectively regularize the ill-posed inverse problem. Building upon the framelet system, we propose a frame-based nonconvex regularization method for Poisson image deblurring. The method is formulated by combining a data-fitting term with the difference of two norms, namely ℓ 1 and ℓ 2 , on the latent image. We solve the optimization problem by combining the difference of convex functions algorithm (DCA) with the alternating direction method of multipliers (ADMM), establishing its convergence. We further employ a simulated annealing procedure and show that proposed algorithm almost certainly converges to a global minimum. Two different approaches are employed to handle the frame-based ℓ 1 norm within the ADMM framework. In particular, the frame-based nonconvex regularization method is also considered for the blind Poisson problem. An effective recovery model and its algorithm are presented. Experimental results demonstrate the effectiveness of our proposed models compared with other models in terms of quantitative metrics and visual quality. • Frame-based nonconvex regularization model is proposed to eliminate Poisson noise and blur from degraded image. • An efficient algorithm with convergence guarantees is proposed. • We study an accelerated algorithm and explore the blind Poisson problem. • Experimental results demonstrate the effectiveness of our proposed models compared with other models. [ABSTRACT FROM AUTHOR]

Topological image analysis is a powerful tool for understanding the structure and topology of images, being persistent homology one of its most popular methods. However, persistent homology requires a chain of inclusions of topological spaces, which can be challenging for digital images. In this article, we explore the use of zigzag persistence, a recent variant of traditional persistence, for digital image processing. To this end, new algorithms are developed to build a simplicial complex associated to a digital image and to compute the relationships between homology classes of a sequence of binary images via zigzag persistence. Additionally, we provide a simple software to use them. We demonstrate its effectiveness by applying it to a real-world problem of analyzing honey bee sperm videos. • Algorithm to build a simplicial complex associated to a binary digital image. • Algorithm computing the homology classes of a list of images via zigzag persistence. • Easy-to-use software (with GUI) to compute the previous algorithm and plot barcodes. • Application to a real-world problem: analysis of videos of sperm of honey bee drones. [ABSTRACT FROM AUTHOR]

Measuring the grain size distribution (GSD) of unconsolidated particles is critical to understanding coastal spreading, riverbed dynamics, and sediment transport. The current study presents a novel gravel automatic sieving (GAS) method designed to improve the accuracy and reliability of particle size analyses. At the macroscopic, the method utilizes the convex hull property of gravel to define the maximum extent of the searched gravel, effectively reducing over and under-segmentation problems. At the microscopic, the accuracy of gravel segmentation is improved by analyzing the color space characteristics of gravel to identify the pixel patches of gravel accurately. To validate the effectiveness of the GAS method, the proposed method was tested in both the laboratory and the field. In the laboratory, four artificial samples were processed using the GAS method, and the results were compared with those obtained using the traditional sieving method. The results showed that the correlation coefficients between the GAS method and the traditional sieving method ranged from 94.3% to 97.8%, and the relative errors ranged from 5.8% to 20.9%, demonstrating the validity of the GAS method. In addition, the application of ImageJ software to manually identify the particle size method (ImageJ method) was also compared with the mechanical sieving method, and the correlation coefficient between the two methods was greater than 98.2%, and the relative error was less than 10.9%, so the ImageJ method can be used as a standardized method to measure the other methods. In the field, sixteen images taken in four different regions and at different times were analyzed using the ImageJ method as a benchmark. The performance of the automatic with image filtering (AIF), BASEGRAIN, and the GAS methods also were compared. The results show that the relative errors range from 28.1% to 94.6% for the BASEGRAIN, 16.8% to 1003.6% for the AIF method, and only 5.6% to 30.7% for the GAS method. As a result, the GAS method demonstrates higher accuracy and stability in complex environments. • The convex hull hypothesis determines the position and maximum size of the gravel. • Proposed search rules for pixel patches based on the shape characteristics of the gravel. • A method for determining gravel pixel patches is proposed based on the macroscopic and microscopic characteristics of the gravel. [ABSTRACT FROM AUTHOR]

The characteristics of Low Surface Brightness Galaxies (LSBGs) are very important for understanding the overall characteristics of galaxies. It is of great significance to search and expand the samples of Low Surface Brightness Galaxies by modern machine learning, especially deep learning algorithm. LSBGs are difficult to discern automatically and accurately with traditional methods because of their obscure features. However, deep learning does have the advantage of automatically identifying complex and effective features. To solve this problem, an algorithm named You Only Look Once version X-CS (YOLOX-CS) is proposed to search LSBG in large sample sky survey. Firstly, five classical target detection algorithms are compared through experiments and the optimal YOLOX algorithm is selected as the basic algorithm. Then, the YOLOX-CS framework is constructed by combining different attention mechanisms and different optimizers. The data set uses images from the Sloan Digital Sky Survey (SDSS), labelled from LSBG in the α. 40 -SDSS DR7 (the cross coverage area of 40% HI Arecibo Legacy Fast ALFA Survey and SDSS Data Release7) survey. Due to the small number of samples in this data set, Deep Convolutional Generative Adversarial Networks (DCGAN) model is used to expand the experimental test data. After comparing with a series of target detection algorithms, YOLOX-CS has a good test result in searching LSBG recall rate and Average Precision (AP) value in two data sets before and after expansion. The recall rate and AP value in the test set without expansion data set reach 97.75% and 97.83%, respectively. In the expanded data set of DCGAN model, under the same test set, the recall rate reaches 99.10% and the AP value reaches 98.94%, which proves that the algorithm has excellent performance in LSBG search. Finally, the algorithm is applied to SDSS photometric data, and 765 LSBG candidates are obtained. [ABSTRACT FROM AUTHOR]

• Colorimetric color reproduction of different multispectral imaging systems applied to cultural heritage studies were examined. • Two methods were devised named Color Transformation Method and Illuminant Method. • The Color Transformation Method is more meticulous and leads to a better result as opposed to the Illuminant Method. • The Illuminant Method is much simpler and still leads to acceptable results. • The two methods have been shown to be applicable to both cameras showing the applicability of the methods developed here to different multispectral imaging systems. Multispectral imaging has long been used in the study of cultural heritage artifacts, particularly manuscripts with low-contrast text. The goal of multispectral imaging systems has largely been to enhance the text by imaging outside the spectral response of the human visual system and by applying various image processing techniques. However, there is a desire to use multispectral images for high quality, true color rendering of the artifacts as well. We use two multispectral imaging systems in this work. One of them is the Multispectral Imaging System for the study of Historical Artifacts (MISHA) which has been demonstrated to have significant utility at a lower cost and better ease of use compared to commercially available systems. This system was specifically designed and built for the purpose of imaging artifacts, particularly manuscripts and works on paper with illegible text due to deterioration and other environmental causes. Given this goal of "discovering" low-contrast text (and other features) on planar objects, the system has not been optimized for color reproduction purposes. The second system is a commercially available MegaVision EVTM Spectral Imaging System. This system is also used for cultural heritage imaging. In this work, we develop an approach to colorimetrically characterize these cameras and illumination systems, adding an option for accurate color reproduction to their capabilities. To do this, we present two different approaches. The first approach we call the Color Transformation Method. Here we use a Macbeth ColorChecker to first linearize the camera photometric response, and then find a linear matrix transformation from the camera response to CIEXYZ tristimulus values. The second approach we call the Illuminant Method. Here we consider each output by the camera as a reflectance factor value at the known wavelength of a narrowband illuminator. We then convert these values to the color of the object in terms of CIEXYZ tristimulus values. We show that the Color Transformation Method using a Macbeth ColorChecker leads to a more accurate result. Meanwhile, the Illuminant Method is much simpler and produces acceptable results, particularly considering accurate color reproduction was not a goal in designing the MISHA camera system. The same methods are applied to both imaging systems to show the robustness and applicability of the approaches developed herein to other imaging systems. Results are shown for both quantitative calibration targets as well as artifacts of interest to the field of cultural heritage studies. It is worth noting that we are not comparing the two imaging systems overall or the color processing software available from MegaVision. Rather, we simply show that the two approaches developed here are applicable to different multispectral imaging systems, from a very cost-effective system, i.e., MISHA to a more expensive one, i.e., MegaVision. [ABSTRACT FROM AUTHOR]

Higher magnetic field strength introduces stronger magnetic field inhomogeneities in the brain, especially within temporal lobes, leading to image artifacts. Particularly, T2-weighted fluid-attenuated inversion recovery (FLAIR) images can be affected by these artifacts. Here, we aimed to improve the FLAIR image quality in temporal lobe regions through image processing of multiple contrast images via machine learning using a neural network. Thirteen drug-resistant MR-negative epilepsy patients (age 29.2 ± 9.4y, 5 females) were scanned on a 7 T MRI scanner. Magnetization-prepared (MP2RAGE) and saturation-prepared with 2 rapid gradient echoes, multi-echo gradient echo with four echo times, and the FLAIR sequence were acquired. A voxel-wise neural network was trained on extratemporal-lobe voxels from the acquired structural scans to generate a new FLAIR-like image (i.e., deepFLAIR) with reduced temporal lobe inhomogeneities. The deepFLAIR was evaluated in temporal lobes through signal-to-noise (SNR), contrast-to-noise (CNR) ratio, the sharpness of the gray-white matter boundary and joint-histogram analysis. Saliency mapping demonstrated the importance of each input image per voxel. SNR and CNR in both gray and white matter were significantly increased (p < 0.05) in the deepFLAIR's temporal ROIs, compared to the FLAIR. The gray-white matter boundary sharpness was either preserved or improved in 10/13 right-sided temporal regions and was found significantly increased in the ROIs. Multiple image contrasts were influential for the deepFLAIR reconstruction with the MP2RAGE second inversion image being the most important. The deepFLAIR network showed promise to restore the FLAIR signal and reduce contrast attenuation in temporal lobe areas. This may yield a valuable tool, especially when artifact-free FLAIR images are not available. • 7 T FLAIR often suffers from signal dropout in temporal lobes. • A subject-specific neural network to reduce the artifacts in post-processing. • The network reconstructs per voxel the FLAIR signal from other structural scans. • Improved SNR and CNR were observed in the attenuated regions. • Further developments may yield deepFLAIR a helpful tool to combat signal dropout. [ABSTRACT FROM AUTHOR]

ADITYA-L1 is India's first dedicated mission to observe the Sun and its atmosphere from a halo orbit around L1 point. Visible emission line coronagraph (VELC) is the primary payload on board Aditya-L1 to observe the Sun's corona. VELC is designed as an internally occulted reflective coronagraph to meet the observational requirements of wide wavelength band and the field of view close to the solar limb (1.05 R Sun ). Images of the solar corona in continuum and spectra in three emission lines 5303 Å [Fe xiv], 7892 Å [Fe xi] and 10747 Å [Fe xiii] obtained with high cadence are to be analyzed using software algorithms automatically. A reasonable part of these observations will be made in a synoptic mode in which the data are processed through a standard pipeline and the resulting products will be made available for public use. The procedure involves the calibration of instrument and detectors, converting the images into the FITS format, correcting the images and spectra for the instrumental effects, and aligning the images (in terms of position angles and image scales) etc. Then, develop image processing algorithms to detect the occurrence of energetic events using continuum images. Also derive physical parameters, such as temperature and velocity structure of solar corona using emission line observations. Here, we describe the calibration of detectors and the development of software algorithms to detect the occurrence of CMEs and analyze the spectroscopic data. [ABSTRACT FROM AUTHOR]

The enhancement of low-quality images is both a challenging task and an essential endeavor in many fields including computer vision, computational photography, and image processing. In this paper, we propose a novel and fully explainable method for image enhancement that combines spatial selection and histogram equalization. Our approach leverages tree-search theory and deep reinforcement learning to iteratively select areas to be processed. Extensive experimentation on two datasets demonstrates the quality of our method compared to other state-of-the-art models. We also conducted a multi-user experiment which shows that our method can emulate a variety of enhancement styles. These results highlight the effectiveness and versatility of the proposed method in producing high-quality images through an explainable enhancement process. • A fully explainable image enhancement method based on reinforcement learning. • The method alternates spatial selection and histogram equalization through deep RL. • An extensive experimentation shows that our method is competitive with SOTA methods. [ABSTRACT FROM AUTHOR]

• The performance of identification algorithms is susceptible to many factors. • Head rotation beyond a 15-degree angle pose challenges to automated systems. • An upward tilt of 10° and higher leads to a notable degradation in performance. • Only a smiling face produced consistently positive log-likelihood ratios. • There is evidence of sex-related bias favoring males in image processing. In today's biometric and commercial settings, state-of-the-art image processing relies solely on artificial intelligence and machine learning which provides a high level of accuracy. However, these principles are deeply rooted in abstract, complex "black-box systems". When applied to forensic image identification, concerns about transparency and accountability emerge. This study explores the impact of two challenging factors in automated facial identification: facial expressions and head poses. The sample comprised 3D faces with nine prototype expressions, collected from 41 participants (13 males, 28 females) of European descent aged 19.96 to 50.89 years. Pre-processing involved converting 3D models to 2D color images (256 × 256 px). Probes included a set of 9 images per individual with head poses varying by 5° in both left-to-right (yaw) and up-and-down (pitch) directions for neutral expressions. A second set of 3,610 images per individual covered viewpoints in 5° increments from −45° to 45° for head movements and different facial expressions, forming the targets. Pair-wise comparisons using ArcFace, a state-of-the-art face identification algorithm yielded 54,615,690 dissimilarity scores. Results indicate that minor head deviations in probes have minimal impact. However, the performance diminished as targets deviated from the frontal position. Right-to-left movements were less influential than up and down, with downward pitch showing less impact than upward movements. The lowest accuracy was for upward pitch at 45°. Dissimilarity scores were consistently higher for males than for females across all studied factors. The performance particularly diverged in upward movements, starting at 15°. Among tested facial expressions, happiness and contempt performed best, while disgust exhibited the lowest AUC values. [ABSTRACT FROM AUTHOR]

No consensus has been established regarding the exact amount of bone grafting in maxillary sinus augmentation. The aim of this study was to estimate the minimum bone volume for sinus augmentation and to investigate the factors that influence the augmentation volume (AV). This study included patients with cone-beam computed tomography scanning. Dome-shaped sinus augmentation was performed virtually at vertical heights (VH) of 3, 5, 7, and 9 mm in Group A (without implantation) and Group B (with implantation). The augmentation angle (AA) and the sinus width (SW) were measured. The AV was measured using the three-dimensional image processing program 3D Slicer. Univariable and multivariable analyses were conducted. This study included 30 patients (120 subjects). In Group A, the mean AVs were 0.062, 0.271, 0.642, and 1.287 cc at VHs of 3, 5, 7, and 9 mm, respectively, in Group B, the mean AVs were 0.037, 0.230, 0.594, and 1.230 cc. Univariable analysis indicated that factors significantly associated with the AV in both groups included SW, AA, and VH (P < 0.001). Multivariable analysis indicated that factors significantly associated with the AV in both groups included AA and VH (P < 0.01). Clinicians can predict the bone volume for sinus augmentation by measuring the augmentation height and angle. [ABSTRACT FROM AUTHOR]

This paper aims to explore the DIC technique for use in wide width tensile testing of geogrids, from specimen preparation to selection of DIC parameters required for analysis to provide a guide for a proper use. A series of monotonically loaded wide width tensile tests were conducted on a PET geogrid to investigate the effects of specimen surface preparation methods and the user-defined DIC parameters. An additional set of tests under cyclic loading was conducted to investigate the effect of the image sampling rate. The results indicate that the speckle pattern (image texture) has a significant effect on the DIC results such that the larger is the speckle size, the greater is the uncertainty level, eventually leading to increased nonuniformity in the calculated strains. Also, it was revealed that a subset size smaller than optimal, typically 20–30 pixels, results in highly localized strain distribution. A similar trend was observed in step size. In addition, the image sampling rate was found to have a significant effect on the DIC-calculated cyclic strains, such that the lower is the image sampling rate, the lower is the calculated cyclic strain. • This paper highlights important considerations for use of the DIC technique in wide width tensile testing of geogrid. • The effects of specimen surface preparation methods and the user-defined DIC parameters are investigated. • Best geogrid specimen preparation technique and optimum user-defined parameters for DIC image processing are suggested. • The importance of selecting an appropriate camera frame rate and its impact on DIC results is discussed. [ABSTRACT FROM AUTHOR]

Traditional interpolation algorithms often fail to meet the precision requirements of ultra-precision machining when applied to super-precision polishing machines. Moreover, the processing of fused silica glass optical components is frequently threatened by mechanical impacts due to their fragility. In order to address this issue, this paper proposes a high-precision motion interpolation method based on fourth-order Runge-Kutta and velocity-flexible planning. This method is designed for open-architecture small multi-axis optical polishing machines to polish quartz glass. The algorithm initially employs composite Simpson's rule to calculate the lengths of sub-paths within the polishing trajectory. Based on these length values, flexible velocity planning is executed to ensure the smooth continuity of velocity, acceleration, and jerk during motion interpolation. This reduces the risk of mechanical impacts that could damage the components during the machining process. The introduction of the adaptive fourth-order Runge-Kutta method significantly enhances the parameter point calculation accuracy of NURBS curves. The incorporation of adaptive principles also maintains a higher processing speed, thereby greatly improving processing efficiency. This method comprehensively addresses both the precision of curve interpolation and execution efficiency. Finally, experimental validation is conducted on an open-architecture small multi-axis optical polishing machine. The proposed method based on FRKVF not only mitigates mechanical impacts resulting from discontinuous acceleration, thereby ensuring the machining quality of optical components, but also satisfies the high-precision requirements for processing fused silica optical elements. • Trigonometric functions enhance curve controllability, reducing the risk of mechanical damage during optical processing. • Adaptive 4th-order Runge-Kutta method improves NURBS curve calculation accuracy and efficiency for ultra-precision machining. • Five-axis small tool polishing machine experiment shows a significant reduction in surface roughness and height difference. • Surface roughness decreased by 34.8% and 24.2%; RMS value by 35% and 23%; peak-valley by 15.5% and 26.8%, respectively. [ABSTRACT FROM AUTHOR]

Objective image quality assessment involves the use of mathematical models to quantitatively describe image quality. FR-IQA (Full-Reference Image Quality Assessment) methods using reference images are also often used to evaluate image processing and computer vision algorithms. Quality indices often use gradient operators to express relevant visual information, such as edges. Fractional calculus has been applied in the last two decades in various fields such as signal processing, image processing, and pattern recognition. Fractional derivatives are generalizations of integer-order derivatives and can be computed using various operators such as the Riemann-Liouville, Caputo-Fabrizio, and Grünwald-Letnikov operators. In this paper, we propose a modification of the FSIMc image quality index by including fractional derivatives to extract and enhance edges. A study of the usefulness of fractional derivative in the FSIMc model was conducted by assessing Pearson, Spearman and Kendall correlations with MOS scores for images from the TID2013 and KADID-10k databases. Comparison of FD_FSIMc with the classic FSIMc shows an increase of several percent in the correlation coefficients for the modified index. The results obtained are superior to those other known approaches to FR-IQA that use fractional derivatives. The results encourage the use of fractional calculus. [ABSTRACT FROM AUTHOR]

This paper proposes an encryption algorithm for crucial areas of a video based on chaos and a neural network, which SVEA (Selective Video Encryption Algorithm). The critical areas of each frame in a video are extracted by deep learning to the encryption system. A one-step encryption algorithm is used to encrypt these critical areas based on chaos, where scrambling and diffusion are simultaneously performed. A new chaotic system 2D extended Schaffer function map (2D-ESFM) is utilized in the encryption system, inspired by the Schaffer function. The system has demonstrated excellent performance through Lyapunov exponents (LEs), permutation entropy (PE), the 0-1 test, and other methods. Additionally, to resist chosen plaintext attacks, the secret key is generated by a neural network, with the critical areas of the video as inputs to the neural network. The chaotic system generates the biases and weights for the neural network. We evaluate SVEA on our dataset (Gymnastics at the Olympic Games) and public datasets. SVEA exhibits strong security characteristics compared to state-of-the-art algorithms and reduces time complexity by approximately 51.3%. • An encryption algorithm for critical areas of a video is proposed. • A 2D extended Schaffer function map (2D-ESFM) with a larger parameter space and a better performance is proposed. • The secret key of the cryptosystem is generated by the neural network, and a one-step encryption method is proposed. • A dataset is built about video encryption, called "Gymnastics at the Olympic Games". [ABSTRACT FROM AUTHOR]

This paper proposes a Generalized Multilevel B-spline Approximation (GMBA) method, which addresses scattered data interpolation problems in image processing. Mathematically, the GMBA provides a better solution for the B-spline control lattice by superimposing identical level B-splines compared with traditional Multilevel B-spline Approximation (MBA). Specifically, the GMBA allows the spacing of next control lattice to be subdivided arbitrarily or remained unchanged, which is determined by a predefined spacing set or the current error level. These improvements bring higher approximation accuracy and more flexibility for algorithm design to avoid over-fitting. In this paper, basic GMBA algorithm and its refined algorithm are compiled for image processing. Finally, six relevant cases are involved to test the GMBA, including surface approximation, image enlargement, image completion, and Salt-and-Pepper (SAP) noise removal. The experimental results show that the GMBA has better performance than the MBA in surface approximation and image processing, performs comparatively fast with the best performance on more than half of the standard test images compared with traditional algorithms, and has partially better performance even than deep learning algorithms. The GMBA can effectively recover meaningful details in images contaminated with even extremely high SAP noise level (up to 99%). • We give a generalized multilevel B-spline approximation (GMBA) method. • GMBA allows the control spacing to be subdivided arbitrarily or remained unchanged. • GMBA offers higher approximation accuracy and greater flexibility than traditional MBA. • GMBA provides superior performance and less run time than many of the state-of-the-art methods for SAP noise removal. • GMBA can recovery meaningful detail at noise levels as high as 99% for SAP noise removal. [ABSTRACT FROM AUTHOR]

• Satellite image (Landsat 8) used to estimate land surface temperature in a Mountainous region. • Single Channel JM&S and Split Window algorithms compared with observed temperatures. • Split Window algorithm depicted lower MAE and closer agreement with observations. Studying Land Surface Temperature (LST) provides various scientific, environmental, and practical advantages. It aids climate monitoring, urban heat island studies, environmental assessments, agriculture, urban planning, infrastructure development, and remote sensing. Algorithm selection depends on research constraints and goals, considering different algorithm strengths and limitations. In this study, the LST around the Sabalan volcanic peak was estimated using Landsat 8 satellite images captured by the OLI and TIRS, employing the Single Channel JM&S and Split Window algorithms. The obtained surface temperatures from both algorithms were converted to air temperature. Subsequently, the pixel air temperatures were compared to the corresponding synoptic station air temperatures of the studied region, considering the satellite's passage time. This comparison was executed using regression analysis (R2 and correlation coefficients) and statistical indices such as Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) to validate the data. The results indicated R2 values and correlation coefficients of 0.04 and 0.97, respectively, for the Single Channel algorithm, and 0.12 and 0.69 for the SW algorithm, signifying a positive relationship and close alignment between these datasets. Furthermore, the examination of the results revealed root mean square error and mean absolute error with minimum errors of 4.20, 3.88, and 8.14, 8.97 °C in the SW method. By assessing the difference between mean LST and the synoptic station air temperatures, the SW approach exhibited lower temperature discrepancies across all stations and lower estimation errors compared to the Single Channel method, thus displaying higher accuracy and closer conformity to the actual temperature. [ABSTRACT FROM AUTHOR]

Multiplicative noise removal is a challenging image processing problem. In this paper, we study a fractional-order nonlinear cross-diffusion system to denoise images corrupted by multiplicative Gamma noise. The system is coupled by two nonlinear, partial differential equations and gray level information, fractional derivative operator is considered in diffusion process to remove high level noise effectively while preserve structure details for texture images and SAR images. We prove the existence of weak solutions and other theoretical properties of the fractional-order cross-diffusion system under some hypotheses. In the numerical aspect, the model is implemented by virtue of the discrete fractional Fourier transform in the frequency domain. Experimental results show that the new system has a good compromise between multiplicative noise removal and structure preservation when compared to other well-known denoising methods. [ABSTRACT FROM AUTHOR]

• Phisically-based thermal infrared images rendering chain for artificial satellite targets. • Assessment and comparison of most relevant pixel-level VIS-TIR image fusion techniques. • Fused noisy image processing within the context of uncooperative space-craft relative navigation. State-of-the-art techniques for vision-based relative navigation rely on images acquired in the visible spectral band. Consequently, the accuracy and robustness of the navigation is strongly influenced by the illumination conditions. The exploitation of thermal-infrared images for navigation purposes is studied in the present paper, as a possible solution to improve navigation in close proximity with a target spacecraft. Thermal-infrared images depend on the thermal radiation emitted by the target, hence, they are independent from light conditions; however, they suffer from a poorer texture and a lower contrast with respect to visible ones. This paper proposes pixel-level image fusion to overcome the limitations of the two types of images. The two source images are merged into a more informative one, retaining the strengths of the distinguished sensing modalities. The contribution of this work is twofold: firstly, a realistic thermal infrared images rendering tool for artificial targets is implemented; secondly, different pixel-level visible-thermal infrared images fusion techniques are assessed through qualitative and quantitative performance metrics to ease and improve the subsequent image processing step. The work presents a comprehensive evaluation of the best fusion techniques for on-board implementation, paving the way to the development of a multispectral end-to-end navigation chain. [ABSTRACT FROM AUTHOR]

The extraction of cellular structure feature on the spherical premixed flame surface faces accuracy challenges. The Schlieren technique was employed to obtain the hydrogen-air premixed spherical flames images in a constant volume vessel at room temperature and atmospheric pressure under an equivalent ratio of 0.8 in this work. A bio-inspired Cellpose 2.0, driven by deep learning, is innovatively introduced to train the cell segmentation model in the combustion field. After labeling and training cells of different shapes and sizes, an efficient and accurate model suitable for cell feature extraction was finally obtained to identify and quantify various cells characteristics, such as number, size, and distribution. Results show that the average precision (AP) during the model online pre-training process reaches 0.625. Meanwhile, the critical flame radius of transition acceleration obtained is 36 mm and the crack length tends to grow linearly after the flame radius exceeds this critical point. Additionally, the average cell area gradually converges to a stable value after the flame radius exceeds the uniform cellularity critical radius. The cell segmentation model obtained in this work can be further used to train different spherical flames under various conditions, helping to develop hydrogen combustion and explosion modelling. [Display omitted] • First application of Cellpose 2.0 in combustion image process yields AP of 0.625 • Quantitative cell information on H 2 -Air flame surfaces achieved with deep learning. • Cells number rapid increase after the flame exceeds critical radius of transition acceleration. • Average cell area gradually converges to a stable value after uniform cellularity critical radius. • Flame propagation exhibits a self-accelerating trend after transition acceleration critical radius. [ABSTRACT FROM AUTHOR]

Over the past two decades, vibrational resonance has garnered significant interest and evolved into a prominent research field. Classical vibrational resonance examines the response of a nonlinear system excited by two signals: a weak, slowly varying characteristic signal, and a fast-varying auxiliary signal. The characteristic signal operates on a much longer time scale than the auxiliary signal. Through the cooperation of the nonlinear system and these two excitations, the faint input can be substantially amplified, showcasing the constructive role of the fast-varying signal. Since its inception, vibrational resonance has been extensively studied across various disciplines, including physics, mathematics, biology, neuroscience, laser science, chemistry, and engineering. Here, we delve into a detailed discussion of vibrational resonance and the most recent advances, beginning with an introduction to characteristic signals commonly used in its study. Furthermore, we compile numerous nonlinear models where vibrational resonance has been observed to enhance readers' understanding and provide a basis for comparison. Subsequently, we present the metrics used to quantify vibrational resonance, as well as offer a theoretical formulation. This encompasses the method of direct separation of motions, linear and nonlinear vibrational resonance, re-scaled vibrational resonance, ultrasensitive vibrational resonance, and the role of noise in vibrational resonance. Later, we showcase two practical applications of vibrational resonance: one in image processing and the other in fault diagnosis. This presentation offers a comprehensive and versatile overview of vibrational resonance, exploring various facets and highlighting promising avenues for future research in both theory and engineering applications. [ABSTRACT FROM AUTHOR]

This research possesses the producing and taking the assessment of a new deep learning structure, namely, Deep Convolutional BiLSTM Hybrid Network, specialized for arrhythmia recognition before ECG records. Through PhysioNet Challenge 2021 dataset, which has collected different styles of the ECG recordings from nine different arrhythmia types, this study is trying to respond to the critical need that non-attendant and accurate arrhythmia detection is required in the medical field. By utilizing both convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) units that allow our model to carry out spatial and temporal operations, which is essential to the native dynamics existing ECG signal, we are able to get in view a more fine-grained analysis surpassing other traditional approaches. The suggested algorithm which has achieved accuracy, precision, recall, and F-score of 98.5%, 98.2%, 98.2%, and 98.4% percent respectively has proven to be a novel and more accurate solution compared to the existing state-of-the-art model when similar kinds of tasks are performed. These results not only reveal the effectiveness of CNNs and BiLSTM toginger in understanding complicated biomedical signs but also shed a light on the prospect of deep learning in raising the standards of dairgocis and health care practices. The research outcome of arrhythmia diagnosis by arranging new standard carpatients would bring a lot of changes to the existing medical informatics that provide a scalable solution that would be implemented to every healthcare institution globally for timely and accurate diagnosis. [ABSTRACT FROM AUTHOR]

• Multispectral imaging for study of the Sarajevo Haggadah. • Non-invasive scientific analysis of medieval illuminated Hebrew manuscripts. • Application of image processing techniques to recover erased text. Over the last two decades, multispectral imaging (MSI) has established itself as the most important tool in recovering illegible text in erased or damaged manuscripts, and to a lesser extent as an aid to the codicological study of manuscript supports and media. Rarely, however, have spectral imaging initiatives involved Hebrew illuminated manuscripts. In 2022, an international team of scholars, imaging scientists, and conservators from the National Museum of Bosnia and Herzegovina and the Lazarus Project of the University of Rochester imaged the Sarajevo Haggadah multispectrally. Produced for a Jewish commissioner and housed at the National Museum of Bosnia and Herzegovina, this 14th-century illuminated manuscript contains, inter alia , a partially erased text of a sale contract on folio 106v* that is now newly legible. Codicological details of the manuscript – ink, stains, type of animal used for parchment – have also benefitted from material analysis via MSI. Herein, we describe the MSI process of the Sarajevo Haggadah and the application of image processing algorithms to recover the erased text on folio 106v*. A complete text of a sale contract is revealed for the first time, providing significant information about the ownership and provenance of the Sarajevo Haggadah at the beginning of the 16th century. [ABSTRACT FROM AUTHOR]

Diffusion MRI of the spinal cord (SC) is susceptible to geometric distortion caused by field inhomogeneities, and prone to misalignment across time series and signal dropout caused by biological motion. Several modifications of image acquisition and image processing techniques have been introduced to overcome these artifacts, but their specific benefits are largely unproven and warrant further investigations. We aim to evaluate two specific aspects of image acquisition and processing that address image quality in diffusion studies of the spinal cord: susceptibility corrections to reduce geometric distortions, and cardiac triggering to minimize motion artifacts. First, we evaluate 4 distortion preprocessing strategies on 7 datasets of the cervical and lumbar SC and find that while distortion correction techniques increase geometric similarity to structural images, they are largely driven by the high-contrast cerebrospinal fluid, and do not consistently improve the geometry within the cord nor improve white-to-gray matter contrast. We recommend at a minimum to perform bulk-motion correction in preprocessing and posit that improvements/adaptations are needed for spinal cord distortion preprocessing algorithms, which are currently optimized and designed for brain imaging. Second, we design experiments to evaluate the impact of removing cardiac triggering. We show that when triggering is foregone, images are qualitatively similar to triggered sequences, do not have increased prevalence of artifacts, and result in similar diffusion tensor indices with similar reproducibility to triggered acquisitions. When triggering is removed, much shorter acquisitions are possible, which are also qualitatively and quantitatively similar to triggered sequences. We suggest that removing cardiac triggering for cervical SC diffusion can be a reasonable option to save time with minimal sacrifice to image quality. [ABSTRACT FROM AUTHOR]

Breast Cancer (BC) is a significant cause in women and is the leading cause of death worldwide. The analysis and diagnosis of breast cancer using medical imaging analysis is a promising research area that facilitates the decision-making of different diseases. This paper provides advanced research papers that mainly define breast cancer detection (BCD) using machine learning (ML) in medical imaging. The research articles are tabulated with their advantages, disadvantages, machine learning methods, the dataset used in their experiments, and the performance metrics obtained from their experimental results. Some research challenges and future research suggestions in breast cancer detection using ML in medical imaging are discussed. This paper has more potential and is helpful for beginners in this research field. [ABSTRACT FROM AUTHOR]

Modic changes are pathologies that are common in the population and cause low back pain. The aim of the study is to analyze the modic changes detected in magnetic resonance imaging (MRI) using deep learning modalities. The sagittal T1, sagittal and axial T2-weighted lumbar MRI images of 307 patients, of which 125 were female and 182 were male, aged 19–86 years, who underwent MRI examination between 2016–2021 were analyzed. Modic changes (MC) were categorized and marked according to signal changes. Our study consists of 2 independent stages: classification and segmentation. The categorized data were first classified using convolutional neural network (CNN) architectures such as DenseNet-121, DenseNet-169, and VGG-19. In the next stage, masks were removed by segmentation using U-Net, which is the CNN architecture, with image processing programs on the marked images. During the classification stage, the success rates for modic type 1, type 2, and type 3 changes were 98%, 96%, 100% in DenseNet-121, 100%, 94%, 100% in DenseNet-169, and 98%, 92%, 97% in VGG-19, respectively. At the segmentation phase, the success rate was 71% with the U-Net architecture. Evaluation of MRI findings of MC in the etiology of lower back pain with deep learning architectures can significantly reduce the workload of the radiologist by providing ease of diagnosis. [ABSTRACT FROM AUTHOR]

• The presence of frost on the evaporator coil degrades the cooling performance. • K-means image segmentation-based frost detection and thickness estimation is proposed. • Frost thickness was estimated using image analysis with an error of 13.69%. • Results were compared with conventional sensors and existing image processing methods. • The method can serve as a reliable feedback source for efficient defrosting. Frost accumulation is a common problem when moisture in the air condenses and freezes on surfaces like heat exchange tubes of refrigeration units. Frost accumulation negatively impacts heat exchange by disrupting the process, reducing system efficiency, and causing operational issues. Therefore, defrosting is mandatory to maintain the rated performance; however, modern automatic defrosting systems rely on sophisticated sensors for frost quantification. These sensors are susceptible to degraded performance with the passage of time under varying environmental conditions. To this end, we introduce a robust and generic image processing-based solution that relies on building a data-driven regression-based model for frost detection and thickness estimation. We evaluated the effectiveness of the proposed method on a newly collected dataset with encouraging performance in terms of a low error margin of 13.69% when compared to conventional capacitive and photoelectric sensors-based frost thickness estimation with error margins of 15.17% and 17.5%, respectively. Similarly, other image processing-based methods, such as Global thresholding, Adaptive mean, and Adaptive gaussian thresholding for segmentation, were compared with the proposed method. Deviations in the error margins were found to be 19.94%, 28.96%, and 27.85%, respectively. These findings highlight the appropriateness of employing K-means for estimating frost thickness. [ABSTRACT FROM AUTHOR]

[Display omitted] Field path planning provides the basis for the autonomous navigation of agricultural vehicles. Existing path planning approaches are constrained to a 2D plane, disregarding the impact of terrain factors on navigation tasks. Furthermore, these methods generate non-global paths, as evidenced by their inability to accommodate the headland turning area while performing path planning based on the actual crop growth in the farmland. Low-altitude remote sensing technology, characterized by its high spatial resolution, timely data acquisition, and strong terrain perception, holds great potential for application in autonomous navigation. This study aims to integrate low-altitude remote sensing technology with path-planning tasks for agricultural vehicles by constructing oblique photography models of fields. The objective is to achieve global 3D path planning leveraging advanced methodologies rooted in deep learning and image processing. Four main steps were included in the proposed method. Low-altitude remote sensing models of field blocks were constructed first. Secondly, the models were converted to image patches for dataset establishment. Thirdly, primary crop row identification was conducted by semantic segmentation. Finally, global 3D paths covering the farmland and headland areas were generated. Tea fields in hilly areas were used to test the algorithm. Experiments revealed that the proposed method could be adapted to different field shapes, row numbers, row spacing, and vehicle turning radii. The proposed method uses deep learning and image processing as the primary technical tools but goes beyond traditional crop row detection to form a global path-planning strategy. In addition, the elevation information enabled by the 3D detection manner allows agricultural vehicles to gain a comprehensive understanding of both their own position and that of their destination. The dataset and the code are available at: https://github.com/ZeroHeading/Global-3D-path-generation.git. [ABSTRACT FROM AUTHOR]

Retinal bipolar and amacrine cells receive visual information from photoreceptors and participate in the first steps of image processing in the retina. Several studies have suggested the operation of aerobic glycolysis and a lactate shuttle system in the retina due to the high production of this metabolite under aerobic conditions. However, whether bipolar cells form part of this metabolic circuit remains unclear. Here, we show that the monocarboxylate transporter 2 is expressed and functional in inner retinal neurons. Additionally, we used genetically encoded FRET nanosensors to demonstrate the ability of inner retinal neurons to consume extracellular lactate as an alternative to glucose. In rod bipolar cells, lactate consumption allowed cells to maintain the homeostasis of ions and electrical responses. We also found that lactate synthesis and transporter inhibition caused functional alterations and an increased rate of cell death. Overall, our data shed light on a notable but still poorly understood aspect of retinal metabolism. [ABSTRACT FROM AUTHOR]

This paper proposes a fundus retinal blood vessel segmentation model based on a deep convolutional network structure and biological visual feature extraction mechanism. It aims to solve the multi-scale problem of blood vessels in the fundus retinal blood vessel segmentation task in the field of medical image processing on the basis of increasing the biological interpretability of the model. First, the subject feature information of the retinal blood vessel image is obtained by using the non-subsampled Residual Bolck convolution main channel. Secondly, combined with the study of biological vision mechanisms, an information processing model of the Retina-Exogenius-Primary visual cortex (V1) ventral visual pathway was established. Gabor functions of different scales are used to simulate the structure of different levels of the visual pathway, and the scale information at different levels is integrated into the corresponding hierarchical stages of the convolutional main pathway network to enrich the information of small blood vessels and enhance the semantic information of the overall blood vessels. Finally, considering the imbalance of the ratio of vessel and nonvessel pixels, an adaptive optimization scheme using hybrid loss function weights is proposed to enhance the priority of blood vessel pixels in the calculation of the loss function. According to the experimental results on the STARE, DRIVE and CHASE_DB1 data sets, the model still achieves superior performance evaluation indicators overall compared with the existing optimal methods in the fundus retinal blood vessel segmentation task. This research is of great significance to the field of medical image processing and can provide more accurate auxiliary diagnostic information for clinical diagnosis and treatment. [ABSTRACT FROM AUTHOR]

Single use plastic packaging is widely accepted to cause significant negative environmental impacts. One option to reduce these impacts is to develop commercially viable and socially acceptable reuse systems. Such closed loop packaging systems require careful consideration of reverse (or circular) logistics, financial modelling, and quality control (fulfilling legal requirements and ethical obligations). One of the most prominent barriers to the concept of reusable packaging for food is safety, dictated by challenges of effective cleaning and pack integrity assessment. This research directly addresses cleaning assurance by investigating the application of ultraviolet (UV) induced fluorescence imaging to optically detect residual food fouling on plastic packaging surfaces. This research reports for the first time the evaluation of UV fluorescence imaging @370 nm for the detection of food fouling on washed PET food pots. The technique is compared against the industry standard, adenosine triphosphate swabbing, and is found to provide a comparable range of sensitivity, full surface coverage, faster assessment, and is suitable for full automation without the use of consumables. The technique is evaluated with respect to integration into industrial process systems. Plastic packing design implications are discussed in this context. [ABSTRACT FROM AUTHOR]

The melting of Antarctic glaciers has become a significant issue as a result of global climate change. Algae on the Antarctic ice/snow is an important part of terrestrial photosynthetic organisms. Monitoring and tracking these algal blooms is crucial for understanding the melting of glaciers in the region. Due to the climatic and natural conditions of the region, traveling to and arranging logistics for monitoring and observing snow algae in the Antarctic continent becomes extremely challenging. To overcome these challenges, a novel algorithm has been developed and designed to automatically detect and analyze green algae (Chlorella sp.) from satellite images. Leveraging the vast and free available data from the Sentinel-2 satellite, the algorithm utilizes its high spectral resolution capabilities, capturing invaluable information from various spectral bands. The algorithm was formulated based on the image obtained on February 28, 2017, where green algae formations were intensively seen in the Ryder Bay. The algorithm was developed based on rule-based detection of algae, with the usage of reflection values from the areas where ground truth was established on this date. The developed algorithm was coded and tested using Python version 3.9. The accuracy analysis of the algorithm was conducted using overall accuracy (OA), F1 score, and Kappa statistical test. As a result of the analysis, the OA, F1 score, and Kappa statistic values were calculated as %91, %88.82-%95.27, and 0.901, respectively. [ABSTRACT FROM AUTHOR]

High resolution (HR) images consist of higher quality and more detail information in comparison to low-resolution images. But obtaining HR images entails higher costs and requires a larger workforce. The solution is using super-resolution (SR) images. Single image SR is the process of creating HR images from a single low-resolution image. Obtaining SR images from low-resolution images is a well-known problem in the domains of computer vision and image processing. Advancement in technology has given rise to many SR algorithms. The perceptual quality assessment of super-resolved images can be used to benchmark the techniques employed for image SR. In this work, a cascaded network-blind super-resolution image quality assessment (CN-BSRIQA) methodology is proposed. The proposed approach works under the cascaded architecture where a convolutional neural network (CNN) is cascaded with a deep belief network (DBN). CNN is employed as a shallow network in the proposed methodology to extract low-level information after partitioning the input image into patches. To assess the visual quality of the SR images, the features retrieved from CNN are incorporated into a DBN. Three databases are used to evaluate the performance of proposed CN-BSRIQA i.e. , SR Quality Database (SRQD), SR Image Quality Database (SRID), and visual quality evaluation for super-resolved images (QADS). When compared to other state-of-the-art methodologies for assessing the visual quality of SR images, CN-BSRIQA outperforms them. For the perceptual quality assessment of SR images, the experimental results reveal that CNN-based techniques outperform techniques based on hand-crafted features. Furthermore, the shallow CNN proposed in the CN-BSRIQA can extract features that are content-independent i.e. , they show better performance over cross-database evaluation in comparison to existing state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

The frequency of potholes and speed bumps on the roads has linearly increased due to ageing, inadequate maintenance, and a growth in the number of vehicles. We have discussed a prototype for the identification of potholes and speed bumps in order to guarantee safe mobility. Such critical road quality data may be made public or shared with local governments and other government agencies for the purpose of corrective action and road maintenance. A pothole detection system using image processing and cloud storage can be used to detect potholes from footage provided by a device, store the information into a cloud database, and analyze the data to identify areas that need repair. The system can also send alerts to users about upcoming potholes and notify road maintenance authorities of new pothole detections. In brief, the system uses image processing to detect potholes and cloud storage to store and analyze the data. It can also send alerts to users and road maintenance authorities. The model was built using YOLOv5 and trained on 70% of the dataset images. It was able to detect potholes with good accuracy in the output images. [ABSTRACT FROM AUTHOR]

One of the structure of economic development is farming involved with niche skills and technologies. More than 25% of total tomato crop production is lost annually because of various plant diseases. The farmers who grow tomatoes face huge economic losses every year, often due to various diseases that can infect tomatoes. The work carried aims to identify these diseases early and accurately, so can be informed well before the damage, which can minimize the waste. Convolution neural network (CNN) techniques, subset of Machine Learning (ML) are demonstrated to be very efficient for image datasets of various complex problems. Specifically, the work is focused to build and train a customized CNN model to classify the leaf images. Here we are using advanced deep learning architectures AlexNet and VGGNet-16 to recognize various diseases from image datasets collected from agricultural sources to develop models. Comparative analysis has resulted an improvement in accuracy by using deep learning architectures and CNN models. These models are responsible for helping to solve distribution problems, checking whether a leaf is healthy or not and, if so, what disease it is. Disease detected early and treated quickly minimizes the cost and improves the quality and quantity of the crop produced. [ABSTRACT FROM AUTHOR]

In recent years, one of the deadliest malignancies is skin cancer. If it is not detected and treated in a timely manner, it is expected to spread to other body parts. An accurate automated system for skin lesion recognition is essential for early detection to save human lives. Although there are many other forms of skin cancer, basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanoma are the three most prevalent. With early identification and appropriate treatment, these three kinds of skin cancer can be successfully treated by using deep learning techniques. One of the main benefits of using deep learning for skin cancer detection is its ability to accurately classify images with subtle differences. In this paper, Image pre-processing is employed at an initial diagnosis for removing the artifacts present in the raw dataset and further Convolutional Neural Network (CNN) is employed to improve classification and detection of skin cancer with improved accuracy. For analyzing enormous volumes of data, R-CNN algorithms are proved to be incredibly effective in terms of accuracy of 84.32%. Due to its precision, effectiveness, objectivity, and accessibility, R-CNN algorithm have proven to be very helpful in the identification and categorization of skin cancer. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel approach for the early detection of skin disorders, aiming to improve the prediction accuracy and precision. Our motivation lies in addressing the challenges posed by the uncertainty in skin lesion features. To achieve this, we employ fuzzy-based segmentation techniques to enhance the quality of skin disorder image processing. Additionally, we explore the integration of intensity data to further refine the segmented images. Our methodology consists of three main steps: segmentation, feature extraction, and classification. We begin by inputting the image into the segmentation phase, followed by the application of a fuzzy c-means clustering process to improve the segmentation output. From the resulting segmented image, we extract features using local binary pattern and local Gabor XOR pattern techniques. These features are then subjected to classification, employing a hybrid classifier that combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. The use of this hybrid classifier is particularly significant, as it leverages the strengths of both CNN and LSTM to enhance the predictive power of our model. Through rigorous experimentation, we have achieved promising results. Our proposed method exhibits an impressive accuracy of 94.6% and precision of 95.5% in comparison to the Conventional FCM Model, which only achieves an accuracy of 87% and precision of 82.5%. [ABSTRACT FROM AUTHOR]

One of the major threats in computer vison and image processing areas is image tarnishing due to noisy pixels. Image tarnishing occurs when clean images are subjected to multiple feature changes, length transmission, or due to improper image capturing. The growth of Autoencoders in Artificial Neural Networks has paved way to efficient noise removal. In this work, an architecture oriented analysis of stacked denoising autoencoders is implemented by considering two perspectives of noise, namely noise as an inverse problem and noise as a residual problem. Autoencoders have been modelled by considering the approaches: Shallow Model, Deep-Series and Parallel Series models. Autoencoders with Skip Connections and Denoising CNNs have also been implemented and analyzed in order to propose an efficient, optimized and best working model for denoising. The dataset used is Common Object in Context (COCO) and the performance of the model is evaluated based on Structural Similarity Index (SSIM) and Peak Signal to Noise Ratio (PSNR). The analysis has presented the impact of the model structures of the autoencoders, which implicitly tend to treat noise as an inverse problem. [ABSTRACT FROM AUTHOR]

Lack of planning and regulations around the landfills has resulted and continues to result in severe environmental damage to the immediate environment around the landfills. Our study systematically reviews the literature to understand different processes of monitoring and analysis of a waste disposal site. It further analyses a satellite footprint from Google Earth Engine, of the western part of India around the urban area of Bombay. For the satellite footprint, we compare different algorithms and satellites for detecting landfills using machine learning. We conduct a supervised classification for satellite images for Land Satellite Applied to Remote Sensing (LANDSAT) (2013 to 2023) and SENTINEL (2018 to 2023) using three different classification algorithms: CART (Classification and Regression Tree), Naive Bayes and SVM (Support Vector Machine). The LANDSAT SVM model was generally the most stable and consistently performed well. The model consistently has one of the highest accuracy scores over the years, followed closely by SENTINEL SVM. The analysis can be replicated to other cities and other large-area studies, and can act as a pointer in doing further analysis of the landfill that can further be used to prevent the effects of the waste disposal site on its surrounding environment. [ABSTRACT FROM AUTHOR]

Today, face recognition is the most prevalent and effective mechanism among various biometric technologies as it is non-invasive method. It helps in identifying or verifying the identity of a person by utilizing its face. But face recognition (FR) can be prone to high error rate. Therefore, efficient feature extraction methods are required for extracting robust facial features to develop efficient FR system. A FR system comprises of mainly three phases, that is, face detection and orientation, extracting facial features and classification of features. The most vital part of an efficient recognition system is extraction of robust features. Hence, extracting facial features is active research area of image processing. Although algorithms have been developed for extracting features, efficient and robust feature extraction still offers great challenge to researchers. Hence, a thorough analysis of feature extraction techniques presented in this work will enable the researchers to select the best suited technique for developing efficient system for recognition of face images. The performance of different feature extraction methods varies under variations in illumination, occlusion and pose etc. It is observed that deep-learning based feature extraction methods outperform wavelet-based methods. After rigorous analysis of various state-of-art techniques it is found that highest accuracy rate of 99.5% is achieved on AR database using wavelet based feature extraction whereas 99.78% is attained using convolutional neural network accuracy and various results achieved till now are stated. [ABSTRACT FROM AUTHOR]

The paper presents advancements in healthcare data capture through the application of image-based extraction techniques, which include sophisticated image processing techniques such as resizing and adaptive thresholding, for prescription information. With the increasing digitization of medical records, automating the extraction of relevant data from prescription documents has become crucial. This research explores the utilization of image processing and optical character recognition (OCR) methodologies to extract prescription information accurately. By converting prescription documents into image format and employing OCR algorithms, the text content is extracted and parsed for critical details such as medication names, dosages, and patient instructions. Notably, our methodology excels in overcoming limitations associated with handwritten documents, achieving an impressive accuracy rate of 98%. This image-based approach offers a streamlined and efficient method for capturing prescription data, reducing manual data entry efforts, and minimizing potential errors. Experimental evaluations demonstrate the effectiveness and accuracy of the proposed approach, highlighting its potential to enhance healthcare data capture and improve patient care. [ABSTRACT FROM AUTHOR]

In the recent scenario, it is important to extract the text from various formats, including handwritten and documents. The ability to accurately detect and recognize text, is a crucial task in many fields, such as OCR systems, document analysis, and image processing. Convolutional neural networks (CNN) and bidirectional long short-term memory (BiLSTM) are used in a unique method for text detection. Additionally, CNN consist of six sequential layers by using Adam optimizer and SoftMax. The proposed approach is designed effectively to handle the variability and complexity of text in both handwritten and document formats. The proposed approach achieved a significant improvement in text detection and recognition accuracy, with 88.5 percentage while comparing with the existing techniques of CNN and LSTM which has an accuracy of 81.8 percentage. [ABSTRACT FROM AUTHOR]