Search

Microfluidic paper-based analytical devices are emerging as promising options for on-the-spot detection of chemical contaminants in water. The coupling of these devices with digital imaging technology has attracted immense interest in developing portable sensor applications. However, the potential of digital techniques still remains to be fully explored. In this work, we integrate digital imaging with microfluidic paper-based analytical devices to develop a portable colorimetric assay for iron. The experimental conditions are optimised using image analysis and the effects of imaging equipment and colorimetric analysis methods on the readout of devices are studied using numerical, graphical and statistical techniques. The experimental results are obtained for the estimation of iron contamination in water samples using a colorimetric assay based on iron (III)-thiocyanate reaction. The digital image acquisition approach using smartphone as imaging equipment is adopted for on-the-spot colorimetric data collection. Image processing techniques are employed to estimate the iron concentration in water from digital images. Greyscale colour intensity obtained from a digital image is identified as a readout of the analytical device and employed for quantitative assessment. The limit of detection for iron is estimated to be 0.26 ppm. The microfluidic approach offers good recovery and repeatability with relative standard deviation of 1.4%. The maximum percentage difference for intensities between the image analysis methods is 4.94% and that between the imaging equipment is 9.96%. The gradients of regression lines for pairwise equipment and method outputs with zero intercept range from 0.9931 to 1.0162 with high values of coefficients of determination. The correlation coefficient values for various paired comparisons (>0.99) suggest strong agreement. Statistical test results suggest no significant differences between methods and between imaging equipment (significance level 0.05). The findings suggest the efficacy of digital imaging and colorimetric analysis for paper-based analytical devices. [ABSTRACT FROM AUTHOR]

Microfluidic paper-based analytical devices (µPADs) have attracted much attention over the past decade because they offer clinicians the ability to deliver point-of-care testing and onsite analysis. Many of the advantages of µPADs, however, are limited to work in a laboratory setting due to the difficulties of processing data when using electronic devices in the field. This review focuses on the use of µPADs that have the potential to work without batteries or with only small and portable devices such as smartphones, timers, or miniaturized detectors. The µPADs that can be operated without batteries are, in general, those that allow the visual judgment of analyte concentrations via readouts that are measured in time, distance, count, or text. Conversely, a smartphone works as a camera to permit the capture and processing of an image that digitizes the color intensity produced by the reaction of an analyte with a colorimetric reagent. Miniaturized detectors for electrochemical, fluorometric, chemiluminescence, and electrochemiluminescence methods are also discussed, although some of them require the use of a laptop computer for operation and data processing. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has been proven to be a powerful method in computer vision and is receiving increasing attention in remote sensing. It is important to analyse the research progress, hotspots, trends and methods in the field of deep learning in remote sensing. First, the main research countries (11), research institutions (20), researchers (20), and the most cited references (20) and hotspots (8) in this field were identified by analysing a total of 2,467 published papers with the bibliometric and visualized analysis (BVA) method. Then, based on the above analysis results, the research basis and the progress of hotspots in this field were summarized by reading a total of 181 relevant papers in detail with the traditional literature combing (TLC) method. The results indicate that deep learning is becoming an important tool for remote sensing and has been widely used in the vast majority of remote sensing tasks related to image processing. Among the following deep learning methods, the convolutional neural network (CNN) is undoubtedly the most widely used model. [ABSTRACT FROM AUTHOR]

Fractional-order derivative is attracting more and more attention of researchers in image processing because of its better property in restoring more texture than the total variation. To improve the performance of fractional-order variation model in image restoration, a truncated fractional-order variation model was proposed in Chan and Liang [Truncated fractional-order variation model for image restoration, J. Oper. Res. Soc. China]. In this paper, we propose a dual approach to solve this truncated fractional-order variation model on noise removal. The proposed algorithm is based on the dual approach proposed by Chambolle [An algorithm for total variation minimisation and applications, J. Math Imaging Vis. 20 (2004), pp. 89–97]. Conversely, the Chambolle's dual approach can be treated as a special case of the proposed algorithm with fractional order α = 1. The work of this paper modifies the result in Zhang et al. [Adaptive fractional-order multi-scale method for image denoising, J. Math. Imaging Vis. 43(1) (2012), pp. 39–49. Springer Netherlands 0924–9907, Computer Science, pp. 1–11, 2011], where the convergence is not analysed. Based on the truncation, the convergence of the proposed dual method can be analysed and the convergence criteria can be provided. In addition, the accuracy of the reconstruction is improved after the truncation is taken. [ABSTRACT FROM AUTHOR]

Video processing is the most emergent area of image processing in Research and Development. This paper, we present some advanced technology interrelated to video and image processing, which will provide a super-resolution high-quality most prominent visible light video for better human visualization and background motions or gesticulations of the human brain. There are two approaches for increasing the current resolution level of an image. The first one is the improvement of spatial resolution by reducing the size of pixels through the techniques of sensor manufacturing by about 40 $ {\mathcal{M}}{\textrm{m}^2} $ M m 2 for a 0.35 $ {\mathcal{M}}\textrm{m} $ M m CMOS process and the second approach is the enhancement of chip size that also enhances the capacitance. In video processing, we mainly focus on object images, i.e. any form of signal processing in which the input is an image and the output is a photograph or a frame of video. So, it will be better to converge over techniques of digital image processing. In the proposed algorithm (MHI Simulink model), edge extraction is performed to find the precious area of MRI and CT-Scan images. Using FPGA, edge detection methods have been implemented over scanned images to get better accuracy. The accuracy of the proposed method has been compared with Prewitt and Sobel's edge detection techniques. The proposed method has given better accuracy than Prewitt and Sobel methods. Finally, this paper shows future directions for researchers to enhance the characteristics of digital image and video processing. [ABSTRACT FROM AUTHOR]

Approximate computing is an emerging paradigm that can tolerate some loss of accuracy to improve the energy consumption and design complexity. Multiplication is one of the important computational components in various digital signal processing (DSP) applications. Improvement of multipliers, as the building blocks of an approximate computing systems, has received significant attention. Compressors are key elements in an approximate multiplier to have an optimal design with high performance. This paper proposes an approximate/exact 4–2 compressor and an exact 5–2 compressor in carbon nanotube field-effect transistors (CNTFET) technology for utilisation in an approximate multiplier. Four efficient designs for utilising the proposed compressors are introduced and analysed for a Wallace multiplier. All of the proposed circuits are analysed in 32 nm CNTFET Stanford technology and are simulated by HSPICE. In addition, as an image processing application of approximate multipliers, this paper compares the quality metrics of the image multiplication for the proposed designs and previously presented approximated multipliers. For example, the proposed schemes provide excellent results in structural similarity index up to 99%, and peak signal-to-noise ratio more than 45 dB. Also, it uses figure of metric (FOM) that includes the accuracy and quality metrics of the approximate multipliers. The simulation results demonstrate the efficiency of proposed designs. [ABSTRACT FROM AUTHOR]

The feasibility of the application of image/signal processing for measuring, marking, matching, and sorting vast quantities of data derived from materials typically found in artworks is presented through four case studies. Different patterns produced by canvas weave structures, surface textures of historic photographic papers, chain line intervals in Rembrandt's printing papers, and watermark variations have been subjected to different modes of computational analysis. The art-historical implications that result from computer-generated algorithms – including dating, attribution, authenticity, and workshop practices – can be considered as "computational connoisseurship." The case studies discussed point to future areas for research. Finally, because of the need for statistically meaningful datasets of images, a practical means of recording internal paper structure is introduced. [ABSTRACT FROM AUTHOR]

Image processing algorithms based on time-frequency analysis are frequently used in testing and researching the mechanical properties of high-temperature materials, especially in aerospace, engines, and ships. However, due to the complexity of the high temperature environment itself, there are many factors that affect the measurement accuracy, among which the existence of thermal airflow disturbance has a particularly significant impact on the digital image correlation method. This paper mainly focuses on two aspects of high temperature edge detection and digital image correlation. On the one hand, the existing algorithm is improved to make it suitable for material property detection in high temperature environment. And relevant experiments are carried out to verify the feasibility and accuracy of the algorithm. The full-field coefficient caching method for fitting initial values proposed in this paper has the premise that the accuracy is comparable to that of the reverse combined Gauss-Newton matching algorithm, but the running speed is improved by about 10%, and the matching accuracy of both is obviously higher than that of the surface fitting algorithm. [ABSTRACT FROM AUTHOR]

Superpixel segmentation can get the middle features in image processing, effectively reduce the dimensionality of the image, and is widely used in image processing fields. To get the regular and compact superpixels in real-time, a superpixel segmentation algorithm based on image density is proposed in this paper. Firstly, the image is uniformly divided according to the number of superpixels to be obtained. Secondly, to get the clustering ability of the pixels, the density image is produced. Thirdly, the seed is chosen in each sub-region block according to the density and then the superpixels are obtained by clustering. During the clustering process, the pixel around the seed should be added into the superpixel if it meets the conditions, and the small supeipixels are merged into the big superpixels around them. Finally, the result shows that the proposed algorithm has the best segmentation effect, and a good balance in accuracy, regularity, and time cost. [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.)

Target segmentation of remote sensing images has always been a hotspot in image processing. This paper proposes a new semantic segmentation technology for remote sensing images, which uses Unet as the backbone and combines attention mechanism and feature enhancement module. The feature enhancement module can enlarge the information of the region of interest (ROI) to improve the contrast of the image; the attention mechanism includes spatial and channel attention modules, which can obtain more detailed information of the desired target while suppressing other useless information. This paper improves the loss function of the traditional Unet. On the basis of the sparse categorical cross-entropy function, the mean squared logarithmic error function is added, which can effectively improve the accuracy of semantic segmentation. The experimental results show that the algorithm has higher computational accuracy than Unet, DeepLabV3, SegNet, PSPNet, CBAM and DAnet while having the computational speed of FCN and Unet in model testing and validation. [ABSTRACT FROM AUTHOR]

The identification of textile fiber materials is a tedious task. Traditional physical or chemical methods rely on specialist knowledge and expensive instruments. Currently, the deep learning-based methods are limited by the lack of sufficient image samples. In this paper, we propose a method for the classification of textile materials based on advanced densely connected convolutional networks (Densenet) using fabric surface images. Firstly, we selected a small sample dataset containing five types of materials and performed some pre-processing, including colour weakening and data enhancement. The lightweight network Densenet was then used as the main body to ensure the low parameters of the network, making it more suitable for the recognition of small sample image datasets. The network is then fused with the attention mechanism, Orthogonal Softmax Layer (OSL) and the depth-separable convolution mechanism, and we call the final network AONet. It has only 0.64 M (million) parameters. In this paper, we tested four metrics of AONet for five types of fabric images, and the results showed that the recognition accuracy was 95.61%. The precision, recall and F1 scores were 94.87%, 94.31% and 94.40%, respectively. [ABSTRACT FROM AUTHOR]

As artificial intelligence was more and more widely used in civil engineering, traditional detection technologies were gradually being intelligent. In order to more accurately identify the apparent diseases of concrete, in the first, this paper collected pictures of four kinds of apparent diseases of concrete, including general diseases, weathering, rebar exposed, and cracks, and used image processing technology to expand the image set; secondly, the deep residual network model were established to get the classifiers of the four apparent diseases of concrete; finally, the transfer learning was used to optimize the deep residual network model to get the best classification result. The results showed that the concrete apparent disease classifier based on deep learning established in this paper can intelligently classify the images of the single disease of concrete. After the optimization of the transfer learning, the accuracy rate reached 91.3%, and the recognition accuracy of rebar exposed diseases had reached 97.6%, which could meet the needs of intelligent detection of concrete diseases in actual projects. [ABSTRACT FROM AUTHOR]

Curved ceramic materials possess corrosion-resistant, heat-resistant, and exceptional hardness, rendering them indispensable in many critical fields, including automotive, aerospace, biomedical, architectural, and artistic applications. The detection of defects in these materials is of paramount importance; but traditional inspection methods fall short due to their unique structural characteristics. Presently, the assessment of curved ceramics predominantly relies on manual inspection, which is fraught with subjective errors and inefficiencies. This paper provides a comprehensive overview of the advancements in machine vision technology as applied to defect detection across various types of curved ceramic materials, including industrial, daily-use, and artistic ceramics. The paper highlights the key factors influencing the development of surface defect detection technology in curved ceramics. It summarises the advantages and disadvantages of traditional machine vision and deep learning approaches for defect detection in curved ceramics and analyzes their respective application scopes. Concluding with an examination of the technical challenges inherent in defect detection, the paper also outlines a prospective trajectory for the advancement of inspection technology in curved ceramic materials. [ABSTRACT FROM AUTHOR]

The quality of weld seams is a core factor affecting the performance of welded components, significantly impacting the safety and reliability of weldment structures. It holds considerable importance in quality control and cost management. Therefore, weld seam inspection is an indispensable part of industrial manufacturing and a key topic in non-destructive testing. This paper comprehensively summarises the main research results in weld seam feature extraction and defect identification based on systematic and detailed literature research. Firstly, the paper compares current mainstream non-destructive testing technologies, such as ultrasonic testing, radiographic testing, and infrared thermography, regarding detection principles, performance accuracy, and efficiency. It summarises their applicable scopes, as well as their advantages and disadvantages, and briefly introduces image processing-based methods for weld seam feature extraction. Secondly, a discussion and analysis of weld defect recognition are carried out, focusing on intelligent recognition methods based on deep learning, such as convolutional neural networks, generative adversarial networks, YOLO, etc. Finally, the outlook and future research trends are presented from various perspectives, such as real-time, adaptability, intelligence, etc. to provide a theoretical basis and technical support for welding quality control and structural safety assessment. [ABSTRACT FROM AUTHOR]

Leukemia is a type of cancer that affects the body's blood-forming tissue, where the bone marrow produces an excessive amount of abnormal white blood cells (WBCs) that do not function properly. The diagnosis of leukemia is typically done by a trained expert who visually observes unique features and determines the type of cancer. However, digital image processing techniques have been improving in the healthcare system, particularly in diagnosing different types of diseases and helping doctors make treatment decisions. This paper presents a system for detecting leukemia in blood microscopic images and classifying them as normal or abnormal (with leukemia) automatically. Two main techniques were used: counting the number of WBCs around red blood cells (RBCs) and measuring the average area of WBCs around a bounding box around each cell. The classification accuracy was calculated at 91.7 and 88.8% for the two techniques, respectively. These techniques can be used as features in machine learning applications, and the system presented is faster and more efficient than traditional diagnostic processes used in hospitals. [ABSTRACT FROM AUTHOR]

Camera calibration will directly affect the accuracy and stability of the whole measurement system. According to the characteristics of circular array calibration plate, a camera calibration method based on circular array calibration plate is proposed in this paper. Firstly, subpixel edge detection algorithm is used for image preprocessing. Then, according to cross ratio invariance and geometric constraints, the projection point position of the center point is obtained. Finally, the calibration experiment was carried out. Experimental results show that under any illumination conditions, the average reprojection error of the center coordinates obtained by the improved calibration algorithm is less than 0.12 pixels, which is better than the traditional camera calibration algorithm. [ABSTRACT FROM AUTHOR]

Image based-corrosion detection has become a widespread practice for steel structures, but fine-tuning their model parameters is time-consuming. Alternatively, convolutional neural networks (CNNs) can also be trained fast and automatically, but they demand a huge training dataset. In this paper, a corrosion detection approach based on an artificial neural network (ANN) whose training dataset size is less than 0.1% of that of typical CNNs is introduced. The input layer of the proposed ANN consists of textural and color properties. In the present work, different color spaces and textural properties are examined for their impact on the robustness of the ANN. Results reveal that the best color channels can be achieved by combining CIE L*u*v* and YUV color spaces. Moreover, energy is selected as the best texture feature with respect to the ANN robustness. The proposed ANN outperforms an available image processing algorithm from the perspective of both speed and accuracy. In conclusion, this ANN can be used for actual applications after a fast and straightforward training step. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) combined with image processing has shown significant improvements through new techniques such as Machine Learning (ML) models. This paper introduces the key methods and algorithms used for Drone image processing. We discuss the benefits and limitations of using ML models instead of classical techniques. Our goal is to classify, categorize and describe the methods that are used in realistic settings of diverse domains of applications. We conducted a systematic literature review where systems presented in the papers were analysed based on their domain, task, technology, and efficiency. By extensively reviewing the existing literature, we successfully identified key themes and trends that emerged across the various research questions. The overall findings of the research emphasise the potential of AI and drone imagery in numerous fields. However, the review also uncovered several challenges that necessitate attention, such as issues related to data quality and the requirement for more advanced AI algorithms. The paper outlines significant innovations in the field and offers recommendations for future research directions. By highlighting cross-disciplinary insights, it delves into methodological approaches, exploring commonalities in AI algorithms and UAVs technologies. [ABSTRACT FROM AUTHOR]

Extracting offshore aquaculture areas from high-resolution remote sensing images is significant for rational planning and dynamic management of aquaculture. However, the complex and changeable characteristics of aquaculture areas will lead to difficulty during high-resolution image processing. In this paper, an improved U-Net deep learning model is proposed to extract offshore aquaculture areas from high-resolution images. This model is improved by the pyramid pooling module (PPM) and up-sampling structure based on the original U-Net model. PPM and the up-sampling structure can better mine semantic and position information in high-resolution images, reduce the interference and adhesion of information in images, and improve the extraction accuracy of unclear aquaculture areas. Based on Gaofen-2 remote sensing image data of Rongcheng Bay in the eastern waters of Weihai City, Shandong Province, the extraction of offshore aquaculture areas is studied. The results show that the F1 score and MIoU of the proposed network model are 93.63% and 87.93%, respectively. Compared with several commonly used deep learning models, the improved U-Net model has a better extraction effect. [ABSTRACT FROM AUTHOR]

Quality control and defect detection are major challenges in industrial environments. The localization of these defects is of crucial importance, as they can affect the performance of manufactured products and even the safety of people. Defect detection methods based on visual sensors and image processing are nowadays the most common approaches. To detect subsurface defects it is common to combine active thermography and deep learning. In this paper, PCT (Principal Components Thermography) is employed to enhance the SNR (signal-to-noise ratio), leading to a significant improvement in the results. Recent developments in this field apply deep learning models for semantic segmentation and object detection. However, the quality of the predictions is not enough to ensure that all quality controls are met. In this paper, a combination of semantic segmentation and object detection is proposed to increase the reliability of predictions. To carry out this combination, a working methodology and two new ensembling strategies are proposed. After comparing the results of the proposed combination with the results of using only semantic segmentation methods in a real industrial scenario, where carbon fiber sheets are used, it is found that the proposal improves the segmentation metrics by a 5% to a 24%. Thus the reliability of the predictions is improved. [ABSTRACT FROM AUTHOR]

Automation of Antimicrobial Susceptibility Test (AST) for faster results and the cheaper cost is gaining importance for effective medical diagnosis. Among all the available methods for AST, disk diffusion is the cheaper one, requires less skill, and it is applicable for telemetry. The diameters of the Inhibition zones are calculated using image processing and computer vision techniques to provide easy and automated data for further processing, however, the result of a particular antibiotic is Susceptible (S), Intermediate (I), or resistance (R). In this paper, the agar plate images, which were prepared for the AST, have been taken with 23 antibiotics and 12 bacteria and the image bank of about 170 images with 513 inhibition zones has been developed. For the diameter calculation of the inhibition zones, four methods are developed. In the first method, the diameter is calculated using the watershed segmentation method which requires manual interference, in the second method, modified edge detection is used instead of edge detection in the watershed segmentation, in the third method a semi-automatic method is developed using segmentation with active contours, and in the fourth one, an automatic method is used based on the fuzzy clustering along with Level set methods (FCLSM). The evaluation is done using kappa and correlation indices. The results show that these methods are giving better results within the tolerable limits for automation. In this paper, the same agar plate image with 11 antibiotics is taken to compare developed methods with the manual method and satisfying results are obtained. [ABSTRACT FROM AUTHOR]

This paper aims to empirically explore the state of practical applications of paraconsistent logics. To this end, we performed an exploratory literature review, analysing papers published between the years 2015 and 2018. Paraconsistent formalisms based on annotated logics are practically the sole type of approach we found to be applied in engineering applications. The engineering problems solved by paraconsistent approaches were mainly in the fields of signal and image processing and decision support. The results of our exploratory review indicate that recent developments in the theory of paraconsistency have not yet been adopted for applications. [ABSTRACT FROM AUTHOR]

Image processing fields, such as separating data from healthcare images, can benefit greatly from using deep learning algorithms. This can be extremely beneficial. For the treatment of someone with a brain tumour, discovering the tumour as soon as possible is critical. The patient's life expectancy would increase if the tumour was discovered sooner rather than later. Medical images typically lack contrast because of noise or because there aren't enough diffusive boundaries in the image. This is because of noise. In order to better understand tumours in medical image segmentation, MRI was used to diagnose the tumour, but it also played a beneficial role in clinical image analysis. Why did an MRI need to be done? This paper will examine how bad a brain tumour is using the hybrid deep learning algorithm, which is what this paper is about. Algorithms help us get the correct answer. Based on the direction of the images taken by MR, there will be a lot of information about how to divide up the pictures. In this way, three separate networks are trained to improve their segmentation results. [ABSTRACT FROM AUTHOR]

Cotton yarn diameter is an important characteristic that reflects the quality of the yarn to a large extent. In this paper, a new method was proposed to determine the diameter of cotton yarn using digital image processing and artificial neural networks. After processing scanned yarn image, the inputs of ANN were represented by yarn count and the white pixels number of edge detection of processed image. The output of ANN was the diameter of cotton yarn. This ANN has been tested on new samples. The results were compared with actual results as well as both empirical formulas (Peirce's method and Mogahzy's method) of yarn diameter which is allocated to calculate the diameter of cotton yarn. ANN has given more acceptable results than both Peirce's relationship and Mogahzy's relationship. To deal easily with the algorithm of this research, a simple graphical user interface has been established. [ABSTRACT FROM AUTHOR]

Potato is one of the most nutritious foods rich in fiber and essential vitamins and minerals. However, potato plants may suffer from diseases such as early blight, late blight, septoria leaf spot or skin diseases such as greening, silver scurf, common scab, black rot etc. These diseases may lead to huge losses in the potato yield annually. Hence, an early prediction of such diseases is required so that they can be controlled at an early stage. Several machine learning, IoT based and image processing techniques have been utilized for this purpose, and this paper aims to survey all such methods and prediction models. A total of 116 studies were analyzed, and out of them, 77 relevant studies belonging to (60%) journals, (34%) conferences and (6%) other sources have been surveyed. It has been observed that most of the selected studies (64%) have used RGB image data (proprietary or PlantVillage dataset). Also, majority of the studies (48%) have worked with imbalanced data. Late blight and early blight are the two diseases that have gained the most attention by the researchers, being included in 58% and 34% of the studies. Moreover, feature extraction/selection has been used only with image data (RGB and hyperspectral). Convolutional Neural Network is the most widely used classifier, followed by Support Vector Machines. This review will help the researchers gain an insight into the work done for disease detection in potato crop and what techniques or diseases need intervention so that yield losses can further be minimized. [ABSTRACT FROM AUTHOR]

Human-Robot interaction plays a vital role in the service robotics field, especially to support old age-dependent people for socio-economic reasons. In this paper, an indigenous 3D printed 6 DoF robotic arm is proposed to support specially-abled people in their independent-feeding process. The objective of the present paper is to find the combination of optimal positional controllers such as CPID, FC, FPID and FOPID, which can handle the cubic reference input signal and can produce an output signal with minimal overshoot and lesser positional error. The reduced positional error helps the robotic arm to accurately reach the destination with minimal oscillations. This would reduce the wastage of food in the middle of the trajectory as well as at the destination. The technical challenge of the paper is to synchronize machine vision, robot kinematics and trajectory planning with robot control for multiple intermediate points, subjected to the cubic input signal. The feeding robotic arm is equipped with Intel© visual depth camera, which is in synchronization with the microcontroller, servo controller, and servo actuators. Here, six intermediate points were identified in the C-space using FK, among which, fuzzy controller was selected for the first two IPs, the GA optimized FOPID was selected for IP3 to IP5 and FPID was deployed for the last IP. The GA: FOPID produced a negligible overshoot of 0.67%, whereas FC and FPID produced an overshoot of 1.4% and 0.8% respectively. The positional error gap between GA: FOPID, FC and FPID was 0.9, and 0.6 Deg/sec respectively. The selection of combination of optimal controllers helps the manipulator to successfully deliver the food without wasting it. The repeatability of the feeding process is ensured by successfully conducting user testing on 20 users for 25 cycles. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) contains hundreds of contiguous spectral bands compared with red green blue (RGB) image, making the precise identification of materials possible by capturing subtle spectral and spatial features. Owing to the special advantage in image processing, convolutional neural networks (CNNs) have been proven to be a successful architecture in HSI classification. However, due to the limitation of receptive field of fixed convolution kernel, CNNs can only extract local features of hyperspectral image. Besides, CNNs fail to mine and represent the sequence attributes of spectral bands because of the limitations of its inherent network backbone. With the emergence of vision transformer, the network can break through the limitation of receptive field and obtain the global correlation of the whole image, but it only focuses on the global information of the object and ignores the local information existing in the sequence and images. Moreover, the correlation of spectral information will be destroyed if traditional methods are directly used to convert hyperspectral images into sequence. To solve this issue, a novel convolution and vision transformer fusion network called CAVFN is devised which contains a new cube-embedding module that can reduce the loss of spectral information effectively by dividing the large HSI cube into several small cubes and encoding them into sequences. More significantly, this paper also combines 1D-CNN and 2D-CNN with vision transformer to extract the local features of sequences and patches, and combines them with global features to obtain better classification results. Finally, this paper evaluates the classification results of the proposed network on three HSI datasets by conducting extensive experiments, showing that our network outperforms other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper presents an area/power efficient design for the Arithmetic Logic Unit (ALU) utilising the FS-GDI approach. The presented ALU is designed in 45 nm, 65 nm and 130 nm node using Cadence Virtuoso simulator. Various ALUI/ALUII designs are presented with different data words. The result of ALUI proves its superiority compared with the traditional CMOS-based design in terms of power consumption, propagation delay and transistor count. The energy of the proposed 4-bit ALU reduced by 32% compared to CMOS based. Scalability of the proposed ALUI and ALUII designs are tested by extending length of the processed bits to 32-bits, through testing the performance of 8-bit, 16-bit, 32-bit ALUs based on the proposed ALUI and ALUII design. It is seen that the energy of the 4-bit ALU reduced by 21.2%, the power efficiency of the DSP and image processing circuits can be improved utilising the proposed designs of the ALUs. The experiment clears the superiority of the proposed ALU units and its suitability for long data words. [ABSTRACT FROM AUTHOR]

Servospheres are robotized observation equipments that produce endless fields for behavior observation of wandering animals. This paper first proposes a markerless visual tracking technique for estimation of the position and the heading direction of wandering animals, since existing techniques for servospheres require special markers or do not estimate the heading direction. The proposed markerless visual tracking technique is then integrated with a visual servo controller for a servosphere. The integrated markerless visual servo controller is available for wandering animals whose shapes in the image plane are represented by long bodies and thinner parts than their bodies. This paper demonstrates that the proposed controller is available for ants, crickets, mantises and spiders, while the shapes of their bodies and legs are different from each other. [ABSTRACT FROM AUTHOR]

Diabetic Retinopathy (DR) is an abnormality related with eye. It is caused due to alteration of the blood vessels present in the retina. If this disease is not treated at the early time, it may lead to permanent vision loss. Numerous image processing techniques including Enhancement, Segmentation, Morphology, Image Fusion, Classification and Registration have been enveloped for the early recognition of DR through blood vessels, exudes, hemorrhages and microaneurysms. This paper deals with a new approach for the analysis of proliferate and non-proliferate DR with the help of Compressive Sensing (CS) technique. CS is a sparse way of effective reconstruction of signals that works mainly on two constraints namely sparsity and incoherence. In this paper, various CS-based approaches are applied to fundus image. The results are studied and the best approach is used for Image Segmentation, Feature Extraction and Classification. [ABSTRACT FROM AUTHOR]

With growing demands for diagnosing COVID-19 definite cases, employing radiological images, i.e., the chest X-ray, is becoming challenging. Deep Convolutional Neural Networks (DCNN) propose effective automated models to detect COVID_19 positive cases. In order to improve the total accuracy, this paper proposes using the novel Trigonometric Function (TF) instead of the existing gradient descendent-based training method for training fully connected layers to have a COVID-19 detector with parallel implementation ability. The designed model gets then benchmarked on a verified dataset denominated COVID-Xray-5k. The results get investigated by qualified research with classic DCNN, BWC, and MSAD. The results confirm that the produced detector can present competitive results compared to the benchmark detection models. The paper also examines the class activation map theory to detect the areas probably infected by the Covid-19 virus. As experts confirm, the obtained results get correlated with the clinical recognitions. [ABSTRACT FROM AUTHOR]

With the recent advances made by deep neural networks for image processing applications, researchers have begun exploring this avenue for pan-sharpening and obtained remarkable results. However, the existing methods are generally limited by their shallow network architectures, resulting in insufficient reconstruction capacities. To produce high-quality pan-sharpened images, this paper proposes a novel neural network for pan-sharpening that uses a multilevel shortcut link and dense block to improve the depth of the neural network. Notably, this paper designs two shortcut links to compensate for the loss of spectral and spatial features during the training process. The experimental results show that the proposed method is superior to the state-of-the-art methods in both subjective visual and objective assessments. [ABSTRACT FROM AUTHOR]

Autonomous robots are designed to support humans in diverse ways including companionship and assistance, as technology evolves, the burden of physical tasks which were performed by humans in the past are getting reduced. Autonomous guidance and navigation are popular fields that use mobile robots to replace humans. These robots are widely used in space, defence, education, and industry and require navigating safely through different environments. A significant aspect of Autonomous Robot Navigation is an obstacle and pedestrian avoidance. Most of the outdoor guiding robots follow the concept of SLAM (Simultaneous Localisation and Mapping) for moving from the initial point to the goal point. Moreover, image processing plays a vital role in the detection and recognition between humans and objects. The existing methodology comprises implementing autonomous tour guide robots are based in embedded systems which has a high degree of recognition accuracy. This paper provides a comprehensive review of the existing autonomous campus and tour guiding robots. This paper is steered at providing a satellite view of these existing assemblies and the advances made with them. [ABSTRACT FROM AUTHOR]

Remote sensing image segmentation plays an important role in many industrial-grade image processing applications. However, the problem of uncertainty caused by intraclass heterogeneity and interclass blurring is prevalent in high-resolution remote sensing images. Moreover, the complexity of information in high-resolution remote sensing images leads to a large amount of background information around objects. To solve this problem, a new fuzzy convolutional neural network is proposed in this paper. This network resolves the ambiguity and uncertainty of feature information by introducing a fuzzy neighbourhood module in the deep learning network structure. In addition, it adds a multi-attention gating module to highlight small object features and separate them from the complex background information to achieve fine segmentation of high-resolution remote sensing images. Experimental results on three different segmentation datasets suggest that the proposed method has higher segmentation accuracy and better performance than other deep learning networks, especially for complicated shadow information. Code will be provided in (). [ABSTRACT FROM AUTHOR]

Digital Circuits applications are expanding rapidly in modern times because they generate correct signals without errors or interferences. These digital circuits play important roles in data storage operation, as well as the implementation of image processing applications on hardware where the power, speed, and area of an electronic device play a significant role, particularly in the field of modern VLSI technology. The digital comparator with more number of bits plays an important role in image processing applications. In the proposed research paper, an attempt is made to design a speed and area efficient 32-bit comparator. To improve the speed of the comparator a modified priority encoder technique is used. It shows that the area of proposed 32-bit digital comparator consumes 573.73 units which are 20% better than when compared with the conventional comparators and the speed improved by 50% when compared with the Conventional Comparators. The proposed implementation is simulated on the 'Encounter(R) RTL Compiler RC14.28'. [ABSTRACT FROM AUTHOR]

The propagation instability of a premixed H2/CO/air mixture flame in an open-ended vertical narrow channel was investigated in this paper. The mixture was ignited at five different ignition positions: IP-50, IP-250, IP-500, IP-750, and IP-950. This paper presents a new method for flame image processing. The flame front curve is generally an exponential outflow from the ignition to the top opening at any ignition. The oscillation frequency increases with the increase of flame front curvature. The flame front curvature fluctuates with time when the oscillation propagation occurs, and the flame decelerates and inverts when the curvature is larger. The dominant frequencies are different depending on ignition position, which has a certain effect on frequency. Five different ignition positions of dominant frequency are 78.00 Hz, 125.07 Hz, 170.5 Hz, 125.1 Hz, 170.7 Hz, respectively. Interestingly, IP-500, IP-750 and IP-950 have secondary frequency values of 356.9 Hz, 357.1 Hz and 331.8 Hz, respectively. The secondary frequency is about twice the dominant frequency, and it is caused by parametric instability. Flame oscillation propagation is affected by dimensionless temperature and Lewis value. The interaction between flame and overpressure wave promotes the deformation and oscillation of the flame front. The overpressure, flame front position, flame front curvature, and flame speed coupled oscillation. [ABSTRACT FROM AUTHOR]

In order to improve the harvesting efficiency of lodging crops, starting from the reel system, this paper combines intelligent image processing algorithms to identify the characteristics of lodging crops. Moreover, this paper optimises the data set, chooses L2 norm regularisation to reduce overfitting, uses exponential decay method to set learning rate, uses moving average model to speed up training convergence speed, improves classification accuracy, and simplifies the structure of the neural network to improve the real-time image recognition effect. A moving average is a statistical estimation that is used to evaluate sets of data by comparing the amounts of various subsets of the entire data set. Simultaneously, this paper improves the traditional reel structure and adds image recognition equipment to recognise crop lodging in real time during harvesting. In addition, this paper reasonably controls the reel system for harvesting, sets the reel working status by identifying lodging crops, and combines image technology to achieve efficient operation of the reel system. Finally, this paper designs experiments to verify the system performance. The research results show that the performance of the system constructed in this paper is good. [ABSTRACT FROM AUTHOR]

The ℓ 1 -regularized minimization has been widely used in many data science applications, and certain special constrained ℓ 1 -regularized minimizations have also been proposed in some recent applications. In this paper, we consider a sphere constrained ℓ 1 -regularized minimization, which can arise in image processing, signal recognition and sparse principal component analysis. Viewing the sphere as a simple Riemannian manifold, manifold-based methods for non-smooth minimization can be applied to solve such a problem, but may still encounter slow convergence in some situations. Our objective of this paper is to propose a new and efficient active-set proximal quasi-Newton method for this problem. The idea behind is to speed up the convergence by separately handling the convergence of both the active and inactive variables. In particular, our method invokes a procedure to effectively estimate active and inactive variables, and then designs the search directions based on proximal gradients and quasi-Newton directions to efficiently treat the convergence of the active and inactive variables, respectively. We show that under some mild conditions, the global convergence is guaranteed, and the complexity is also performed to reveal the computational efficiency. Numerical experience on the ℓ 1 -regularized quadratic programming and sparse principal component analysis on both synthetic and real data demonstrates its robustness and efficiency. [ABSTRACT FROM AUTHOR]

Stripe noise is a prevalent issue in infrared imaging systems, characterized by its distinctive directional features, which often appear as vertical lines across the image. This type of noise can significantly degrade the quality of the captured images, making it crucial to address and mitigate its effects. This paper presents an effective strategy to tackle this problem by transforming it from a 2D image issue into a 1D signal problem, enabling efficient resolution of stripes in infrared images. By understanding the characteristics of stripe noise, the proposed algorithm effectively solves the problem by first computing the column average of the noisy image, extracting stripe components from this one-dimensional signal, and effectively removing the stripes without blurring image details. This approach has been tested on numerous images with varying noise levels, demonstrating exceptional denoising performance compared to state-of-the-art methods. The results show marked improvements in visual quality, especially around edges and smooth areas, without requiring complex algorithms or iterative processes. [ABSTRACT FROM AUTHOR]

In this paper, a digital bio-dosimeter (DBD) with a square window size of 7 × 7 pixels is proposed for the quantitative detection of the deformed biological cells irradiated by X-rays with different energies and γ-rays from 60Co. The basic idea of the DBD is to compute the energy of the bio-dosimeter window size by summing up the entire gray levels. Peripheral blood films (PBFs) from male albino rats irradiated by ionizing radiations are prepared and photographed using an Automatic Image Contour Analysis system with high magnification to produce a 2D image. The surf function in MATLAB is used to convert the 2D image to a 3D shaded surface to resample the date more finely. The proposed DBD shows that the computed energies on the boundaries of the normal RBCs are nearly the same, while the computed energies on the boundaries of the deformed cells are significantly larger. [ABSTRACT FROM AUTHOR]

In this paper, we propose an inertial proximal splitting method for solving the non-convex optimization problem, and the new method employs the idea of inertial proximal point to improve the computational efficiency. Based on the assumptions that the sequence generated by the new method is bounded and the auxiliary function satisfies the Kurdyka–Łojasiewicz property, the global convergence analysis with a more relaxed parameter range is proved for the proposed method. Moreover, some numerical results on SCAD, image processing and robust PCA non-convex problems are tested to demonstrate the effectiveness and superiority of the proposed method. [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.)

Recent works in image perception and multimedia technology have paved the way for automated analysis of visual arts. Intelligent painting based on image perception, processing and identification in multimedia enterprise is the trend. In this paper, we use a Cross- Contrast Neural Network (CCNN) model to automatic art identification in oil painting. To achieve this point, we first retrained a tailored CNN network to extract features of oil paintings and then calculated the cross-contrast probability map utilising the contrast information to measure the similarity between input images. We aim to combine IBS with CNN to facilitate the training progress and reduce the difficulty of finetuning the parameters of CNN. To demonstrate the effectiveness of our approach, we introduced the Selected-Wikipaintings dataset, containing over 5000 images painted by 20 artists in various styles. The average accuracy of the classification task in 20 artists achieved 85.75%, which proved to be more accurate than the general method in artists identification task. Our extensive experimental evaluation shows that CCNN owns better classification performance in small data-set multi-classification scenes. [ABSTRACT FROM AUTHOR]

In this paper, the energy characteristics of Gabor texture are used for cloud detection in high-resolution multispectral images. First, the satellite remote-sensing image is divided into superpixels using simple linear iterative clustering (SLIC), and then, the energy characteristics of Gabor texture and spectral characteristics are computed by extracting the texture features of the superpixels. The features of the cloud superpixels are used as the learning sample of the support vector machine (SVM) classifier, and a classification model is obtained by training the SVM classifier. Finally, a cloud-detection experiment is conducted for various sensor images with three visible bands and one near-infrared band. The experimental results showed that the proposed method provides an excellent average overall accuracy for thick and thin clouds in a complex background of forests, harbours, snow and mountains. The characteristic parameters of this paper are not limited by the image parameters; thus, they provide good results and universality for various types of sensors. [ABSTRACT FROM AUTHOR]

The main goal of this paper was to check if either the number or the composition (the arrangement or placement) of knots visible on the furniture fronts could be effective predictors of their relative visual attractiveness. Five different groups of human experts (73 people total) filled out a special online questionnaire, which contained 99 furniture front photos. The experts were asked to rate the relative attractiveness of the fronts using the 5-point Likert scale. It was found that an increase in the number of knots in the range of 0–4 significantly reduced the relative attractiveness of the front, but a further increase (from 4 to 8) made no statistically significant difference. Furthermore, the opinions of all expert groups turned out to be very similar, regardless of their professionalism in the field of interior or furniture design. No other (than the number of knots) predictors of the attractiveness of the fronts (such as the arrangement or placement of visual knots) could be found. The effectiveness of the number of knots as the only predictor of the visual attractiveness of cabinet doors (made of pine wood) was 61% or 87%, depending on the form of classification. [ABSTRACT FROM AUTHOR]

Thirty years into its development, additive manufacturing has become a mainstream manufacturing process. Additive manufacturing fabricates products by adding materials layer-by-layer directly based on a 3D model. It is able to manufacture complex parts and allows more freedom of design optimization compared with traditional manufacturing techniques. Machine learning is now a hot technology that has been used in medical diagnosis, image processing, prediction, classification, learning association, regression, etc. Currently, focuses are increasingly given to using machine learning in the manufacturing industry, including additive manufacturing. Due to the rapid development of machine learning in additive manufacturing, a special issue 'Machine Learning in Additive Manufacturing' in International Journal of Computer Integrated Manufacturing is organized. This paper gives a comprehensive understanding of the current status of machine learning enhanced additive manufacturing technologies for this special issue. Discussions and future perspectives are also provided. [ABSTRACT FROM AUTHOR]

The study of soil cracking is becoming increasingly important because of rising global temperatures and frequent natural disasters. And it poses a huge threat to the infrastructure. In the literature, soil cracking has been tackled by many researchers with various methods. The desiccation cracking process is influenced by various factors, such as soil thickness, temperature, and wet-dry cycles, which makes the process extremely complex. A large number of theoretical studies, indoor experiments and numerical simulations have been carried out. Many advanced techniques, such as X-ray CT and image processing, have also been used in this process. In this paper, the research work of soil cracking is briefly reviewed and summarized, including cracking mechanism, influencing factors of cracking, the comparison of different research methods. The review also lists current limitations and some promising directions for future research. [ABSTRACT FROM AUTHOR]

Road surfaces experience fatigue stress and loading, which often lead to cracks on the surface. The cracks might cause serious damage, and therefore, early detection can reduce the road maintenance cost. Traditional inspection methods are carried out by humans and are slow, costly and hazardous. To improve accuracy and reduce the hazards of current crack detection methods, this paper proposes a new autonomous crack detection system (ACDS) that can be used in any autonomous vehicles (UAVs). ACDS consists of three stages: image acquisition, image processing, and classification. The image processing stage consists of five parallel filtering methods, which remove noise and extract features from the images. In the classification stage, five deep belief network (DBN) classifiers separately analyse the images to detect cracks. The dataset used in this paper contains 15,000 RGB and infrared images, with or without cracks. The results show the high precision of the proposed system. [ABSTRACT FROM AUTHOR]