Digital Image Processing Techniques Research Articles

Use of artificial intelligence in banknote reconstruction

Banknotes may be damaged during various events, such as floods, fires, insect infestations, and mechanical or manual shredding. Disaster victims might need to perform banknote reconstruction when applying for currency exchange, or investigative agencies might need to conduct such reconstruction during evidence collection. When the number of banknote fragments is small, they can be manually assembled; however, when this number is large, manual assembly becomes increasingly difficult and time-consuming. Therefore, an automated and effective method is required for banknote reconstruction. The process of banknote reconstruction can be considered similar to solving a large-scale jigsaw puzzle. This study employed an artificial intelligence (AI) system to reconstruct damaged banknotes. A robotic arm was used to replace manual separation and automated digital image processing techniques, and AI image registration technology, deep learning, and logical operations were utilized. A deep convolutional neural network was used to estimate the relative homography between images, and fragmented banknotes were mapped to a reference banknote for image transformation, thereby reconstructing the damaged banknotes. Additionally, a repetitive matching method was established to optimize the matching results to achieve the best possible mapping and enhance validation efficiency.

Comparing inpainting techniques for urban object restoration from orbital images

Abstract. Based on the comparison of three established inpainting techniques, namely Criminisi, Beltamio, and Galerne and Leclaire, our study aimed to identify the most effective method for road restoration after extraction and detection using a Mathematical Morphology operators combined with hybrid techniques of digital image processing in remote sensing images. While all techniques were evaluated based on both visual analysis and quantitative metrics, the Criminisi approach emerged as the better choice. Despite introducing some additional noise, this technique demonstrated superior performance in terms of Completeness and overall Quality, achieving approximately 95.23% and 94.56%, respectively. Its ability to accurately reconstruct linear geometries while effectively removing existing noise highlighted its suitability for road restoration tasks.

Selection of Optimum Enhancement Technique for the Discrimination of Alkali Granites and Syenites around Suryamalai Batholith of Central Tamil Nadu, India

Image processing techniques such as Band Ratio, Principal Component Analysis, Supervised, Unsupervised classification and Reclassification techniques are generally used as an enhancement technique for alteration zone demarcation and lithological discrimination in geosciences environment. In the present study, Landsat OLI satellite imagery has been utilized to produce various combinations of image enhancement to discriminate alkali syenite and alkali granite of Proterozoic age. These techniques were also used to differentiate three phases of granites reported in Suryamalai Batholith which is very difficult to map by conventional method due to its rugged topographic nature. 12 types of enhancement techniques were applied to differentiate rock alkali syenite from granite, however only few methods such as Kaufmanns ratio, ratio of 5/7, 3/1 and 3/5 and supervised classification were found to be suitable for the discrimination of those rocky types. Band ratio 5/7, 3/1 and 3/5, Crosta analysis and thermal reclassification techniques significantly brought to light the difference between the metamorphic rocks such as fissile hornblende biotite gneiss and hornblende biotite gneiss of Archaean age. Similarly, phase I and phase III granites were perfectly discriminated from all the image enhancement techniques. It is differentiated mainly based on its grain size and mineral variation between these two rock types. Study revealed that standard digital image processing technique can be effectively used for lithological mapping.

Dynamics of Land Use and Coverage and its Impacts on the Upper Moquegua River Hydrographic Basin

Objective: Evaluate; identify and qualify the impacts of the dynamics of land use and coverage in the years 1973 and 2016 in the Hydrographic Basin and in the marginal strip of the Upper Moquegua River in Moquegua Peru. Theoretical framework: In the area studied, human activities and global climate change have disturbed the balance of natural systems, causing major impacts and complex consequences on land use and cover. Method: Digital image processing techniques and supervised classification using the maximum likelihood method were used, followed by matrix editing with refinement of the base and thematic cartography, reaching 94.4% accuracy in interpretation for the year 2016. Result and discussion: The main changes identified regarding the dynamics of land use and coverage were similar in the basin area and in the marginal strip. An increase was noted in the urban area of the entire basin of 568.53ha (1,097.96%) and 134.86ha (1,263.33%) in the marginal strip, which may have been largely influenced by mining activity, which was not observed in 1973, but present in 2016, occupying an area of 1,092.77ha throughout the basin, with 171.99ha in the marginal strip. The areas that had the greatest reduction were those of the glacier, with 2,275.39ha (-93.33%) in the entire basin and 83.77ha (-100.00%) in the marginal strip. Conclusion: With the results of this research, we hope to contribute to the literature related to the topic and to actions and public policies that encourage the appropriate use of land in the Upper Moquegua River Basin, especially in environmental protection areas.

A low voltage semiconductor arc discharge plasma actuator with long discharge gap distance

Long-gap spark discharge is beneficial for plasma-assisted combustion. However, the longer the discharge gap, the higher the breakdown voltage required, which is not feasible in practical applications. In the present study, based on a custom-built semiconductor, a long gap discharge plasma actuator is designed, and the breakdown voltage is relatively low compared with the normal spark discharge method. The breakdown discharge voltage for 25 mm gap at atmospheric pressure is only 3.24 kV. The discharge characteristics were investigated in detail. The influence of voltage, capacitance, and the semiconductor geometric parameters on the discharge characteristics is investigated. Based on a high-speed camera, the temporal and spatial long gap discharge process was captured firstly. Combined the discharge waveforms and images, the discharge process of the semiconductor arc discharge plasma actuator is divided into four stages: applying high voltage, surface discharge, air breakdown, and conduction discharge. Using digital image processing techniques, the influence of voltage, capacitance and air gap on surface discharge evolution velocity was studied.

Hidden Archaeological Remains in Heterogeneous Vegetation: A Crop Marks Study in Fortified Settlements of Northwestern Iberian Peninsula

This study evaluates the effectiveness of multispectral imaging via Unmanned Aerial Systems (UAS), in combination with advanced digital image processing techniques, for the detection and mapping of archaeological sites within diverse landscapes. The research focuses on six case studies located in the northwest of the Iberian Peninsula, a region marked by complex vegetation patterns and varying topography. The primary objective is to assess the potential of these non-invasive remote sensing techniques in identifying crop marks associated with buried structures from ancient, fortified settlements. By means of Principal Component Analysis (PCA) and vegetation indices, the study aims to pinpoint areas of interest that may indicate the presence of archaeological features, while effectively distinguishing them from modern disturbances or natural terrain variations. The research encountered several challenges, including seasonal variations in crop conditions and recent land-use changes. The methodology successfully identified distinct archaeological features. In some instances, natural vegetation variability, typically seen as an obstacle, enhanced the visibility of crop marks, aiding in the detection of underlying structures. These results offer a cost-effective and scalable option for preliminary archaeological surveys, particularly in refining survey methodologies and guiding future excavation efforts aimed at uncovering and preserving ancient, fortified settlements in the region.

Evaluation for coarse aggregate distribution of asphalt mixtures based on the two-dimensional digital image analysis

Meso-structure is one of the major sources of macro-performance in asphalt mixtures. The research on aggregate distribution state is of great significance for the further improvement of asphalt mixture macro-performance. However, the variations of research methods among prior works hamper the deduction of the holistic potential and promising directions of coarse aggregate distribution analysis from current research findings. This work comprehensively verified the quantifying ability of aggregate distribution state indices and their correlation with rutting performance under an advanced digital image processing technique and a wide range of asphalt mixture types, and aims to provide a reference of the holistic potential and promising directions of coarse aggregate distribution analysis for subsequent research. To this end, eleven typical asphalt mixtures’ aggregate distribution state and rutting performance were measured, quantified, and correlated. The results show that Kpe nears or more than 0.56 can be the sign of coarse aggregates effectively interlocked while it nears or less than 0.26 is the opposite; Uarea nears or less than 2 % can be the sign of reaching a coarse aggregate distribution equilibrium; Δorien approaches 6.21 can be the sign of reaching a coarse aggregate orientation equilibrium; mixtures with a nominal maximum aggregate size of 10 mm are disabled in gathering contact chains. Moreover, these coarse aggregate distribution state quantifying indices proposed in existing research can indeed describe the meso-structural features of asphalt mixtures to a certain extent. However, these indices fail to capture the underlying meso-structural features relating to rutting performance and lead to limited applicability. Furthermore, the poor performance of these coarse aggregate distribution state quantifying indices in the global fitting mainly comes from their incompatibility with changes in nominal maximum aggregate size.

Gradient Magnitude Based Image Classification and Edge Detection for Pattern Recognition in Grayscale Images

Image classification is a crucial technique in digital image processing, used in various applications such as object recognition, surveillance systems, and medical image analysis. This research explores the use of gradient magnitude-based edge detection and Robert's Cross methods in improving the classification accuracy of grayscale images. Edge detection is used to identify object boundaries, while gradient magnitude amplifies intensity differences, thus clarifying existing patterns. Through experiments conducted on grayscale images, the results show that this method is able to detect edges with significant accuracy. The gradient values obtained from the combination of Rx and Ry matrices give a strong indication of the presence of edges, which plays an important role in image classification. With an accuracy of 75%, the method proved to be effective, although there are still challenges in dealing with images with high noise or low contrast. The conclusion of this study shows that the combination of edge detection and gradient magnitude is a promising approach for image classification, providing results that can be applied in various domains, including medical and surveillance. Further research is recommended to optimize this approach and extend its application to more complex datasets.

Utilizing an Ex Vivo Skin Penetration Analysis Model for Predicting Ocular Drug Penetration: A Feasibility Study with Curcumin Formulations

Objective: This study aimed to investigate the feasibility of using the digital image processing technique, developed to semi-quantitatively study dermal penetration, to study corneal penetration in an ex vivo porcine eye model. Here, we investigated various formulation strategies intended to enhance dermal and corneal bioavailability of the model hydrophobic drug, curcumin. Methods: Several formulation principles were explored, including oily solutions, oily suspensions, aqueous nanosuspension, micelles, liposomes and cyclodextrins. The dermal penetration efficacy was tested using an ex vivo porcine ear model previously developed at Philipps-Universität Marburg with subsequent digital image processing. This image analysis method was further applied to study corneal penetration using an ex vivo porcine whole-eye model. Results: For dermal penetration, oily solutions, oily suspensions and nanosuspensions exhibited the least penetration, whereas liposomes and cyclodextrins showed enhanced penetration. Corneal curcumin penetration correlated with dermal penetration, with curcumin loaded into cyclodextrins penetrating the deepest. Conclusions: Overall, our study suggests that the image analysis method previously developed for ex vivo skin penetration can easily be repurposed to study corneal penetration of hydrophobic drugs.

Deep learning assisted characterization of bubble behavior in a gas-solid fluidized bed with binary particle mixtures

Gas-solid fluidized beds are widely applied as chemical reactors, and the fluidization quality in the bed is closely related to bubble behavior. Digital image processing is a commonly used non-invasive method for bubble behavior analysis, but it is usually constrained by experimental conditions such as lighting, making identification of bubble and emulsion phases still challenging. Herein, deep learning is applied in this study to optimize traditional digital image processing techniques. By evaluating different deep learning models (FCN, DeepLab V3, U-Net), rapid and accurate identification and segmentation of bubble images can be achieved, and the U-Net model performs best, achieving an identification accuracy of 99.05 %. Further application of U-Net to analyze bubble behavior demonstrates that deep learning methods enable efficient and accurate identification of bubbles and real-time analysis of bubble behavior, highlighting the significant potential application of deep learning in the field of complex hydrodynamics in fluidized beds.

Measures of angularity in digital images.

In light of the growing interest in studying the affective and aesthetic attributes of curvature, the present paper describes four digital image processing techniques that can be used to objectively discriminate between angular and curvilinear stimuli. MATLAB scripts for each of the techniques accompany the paper. Three studies are then reported that evaluate the efficacy of five metrics, derived from the four techniques, at quantifying the degree of angularity depicted in an image. Images of simple polygons (Study 1), artistic drawings of everyday objects (Study 2), and real-world objects, typefaces, and abstract patterns (Study 3) were analyzed. Logistic regression models were used to determine the relative importance of the metrics at distinguishing between angular and curvilinear items. With one exception, all of the metrics were capable of distinguishing between angular and curvilinear items at a level above chance, but some metrics were better at doing so than others, and their discriminative capacity was influenced by the characteristics of the image. The strengths and limitations of the metrics are discussed, as well as some practical recommendations.

A Review on ML and DL Techniques in Detecting Plant Diseases

In Our country, Agriculture is the main occupation of the people. Plant diseases are a major problem today as they affect the quality and production of agricultural production. Most plant-borne diseases are caused by viruses and fungi. Identifying the diseases in early stage by manual power is not possible in large sector of Area. Subsequent maintenance of plants conditions are major challenging task. To overcome this problem in Agriculture, we use Image Processing Technique to identify the disease in beginning stage . To Apply Image Processing Technique, we have to undergo certain Image concepts that deals with image acquisition, image pre-processing, image segmentation, feature extraction and classification of disease. This Methodology reduces the destruction of plants and make the crop production high. The digital Image Processing Technique is the main solution to solve the problems in Plant diseases by identifying the plant diseases in early stage. It is very much useful to the Farmers who are facing plant diseases problem in their Agriculture Area. Many techniques are used to identify the diseases in plants using classifiers such as , K-Nearest Neighbors ,Support Vector Machine methods etc. This paper gives the overview of available methods for plant disease detection

Design of optical performance for self-luminous pavement materials

The lower visibility in the nighttime environment makes higher accident risks during driving. Using self-luminous materials in pavement construction can effectively improve the luminance of load surface, thus significantly improve nighttime driving safety. This study has designed three types of self-luminous pavement materials (SLPM) with different optical properties by incorporating long-persistent luminescent aggregates into the mixture and using polymer binders with varying degrees of light transmittance, such as transparent polyurethane, transparent asphalt, and traditional asphalt. On this basis, utilizing digital image processing techniques to compare the optical performance differences among these three SLPM and established corresponding computational models based on the obtained data to enable efficient and accurate evaluation of the optical properties of pavement materials. The experimental results indicate that the durability performance of SLPM gradually diminishes over time, and this degree of attenuation is negatively correlated with the light transmittance of the binder. Specifically, a higher light transmittance of the binder results in a smaller decline in SLPM durability, whereas a lower transmittance leads to a more significant reduction. The optical performance calculation model established by this research can predict the reflective performance of SLPM through the optical parameters of aggregate, binders, and the doping amount of long persistent luminescent materials. In addition, the model can accurately calculate the minimum content of self-luminous materials according to the optical requirements required by the project, which can provide a reference for the performance evaluation of self-luminous pavement materials and the selection of optimal proportioning scheme.

Comparison of YOLOv8 Models for Aircraft Detection in Airport Apron Using Digital Image Processing

Airport safety can be improved by efficient air traffic management, which monitors aircraft parking spots and controls their movement into them more efficiently. In addition to emergency situations, it can assist in accurately inspecting airport areas. Management costs can be reduced by reducing the workload of personnel in controlling and helping manage air and ground traffic. This research focuses on comparing the performance of various YOLOv8 models (YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8nl, and YOLOv8nx) in an automated aircraft detection system using digital image processing techniques. The methodology involves collecting a dataset of 1,000 airport apron images with parked aircraft, dividing them into 900 training images and 100 testing images. The YOLOv8 models are trained on the training dataset, and their performance is evaluated on the testing dataset using confusion matrices. Experimental results reveal that YOLOv8nx achieves the highest average aircraft detection performance, with a precision of 0.94, recall of 0.74, and f1-score of 0.83. Additionally, YOLOv8n demonstrates the highest processing speed at 0.95 milliseconds. Consequently, YOLOv8n is suitable for applications requiring high-speed processing, while YOLOv8nx is ideal for tasks demanding the utmost performance efficiency.

Development of Digital Image Processing Algorithms via FPGA Implementation

Real-time image processing is one of the fundamental elements in achieving IR 4.0. The rapid development of digital image processing techniques has enabled various applications in fields such as healthcare, transportation, and manufacturing. People are seeking higher-performance image processing as traditional image processing is no longer fulfilling the demands. FPGA-based digital image processing has become one of the choices for the public due to its parallel pipelining, which enables shorter processing time and better performance. Several digital image processing algorithms have been developed in this project, which are gray level transformation, brightness manipulation, contrast adjustment, thresholding, and inversion. They are the most popular algorithms used in digital image processing. Microsoft Paint is used to convert the format of the color input image to bitmap format, followed by MATLAB to convert it into a hexadecimal file to be read and written in FPGA. Platforms such as ModelSim Altera and Intel Quartus II are used to write Verilog HDL for digital image processing algorithms. As a result, five hexadecimal files are obtained from the simulation. The output hexadecimal files are further processed in MATLAB to generate respective images.

Quality Assessment of Rice Using Convolution Neural Networks and Other Machine Learning Techniques- A Comparative Study

Rice holds its position as the most widely cultivated crop worldwide, its demand steadily rising alongside population growth. The precise identification of grains, especially wheat and rice, holds significant importance as their ultimate utilization depends on the quality of grains prior to processing. Traditionally, grain identification tasks have been predominantly manual, relying on experienced grain inspectors and consuming considerable time. However, this manual classification process is susceptible to variations influenced by individual perception, given the subjective nature of human image interpretation. Consequently, there is an urgent need for an automated recognition system capable of accurately identifying grains under diverse environmental conditions, necessitating the application of digital image processing techniques. In this study, we focus on grading five distinct varieties of rice based on their quality, employing a range of convolution neural networks (CNN) namely, Efficientnetb0, Googlenet, MobileNetV2, Resnet50, Resnet101, and ShuffleNet. The performance of CNN towards identification and grading of rice grain is also compared to that of other parametric and Non-parametric classifiers namely, Linear Discriminant Analysis (LDA), K-Nearest Neighbor (K-NN), Naive Bayes (NB), and Back Propagation Neural Network (BPNN) using Gray Level Co-occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRLM) based texture features. The image dataset comprises five grades of rice, each containing 100 images, resulting in a comprehensive collection of 500 samples for analysis. It is observed that, Convolution neural networks can grade five different qualities of rice with highest accuracy of 64.4% in case of GoogleNet. Results show that, rice grading using texture features performs better with highest accuracy of 99.2% (using GLCM) and 93.4% (using GLRLM).

Investigation of aggregate gradation on air voids distribution in porous asphalt concrete using X-ray CT scanning images

Porous asphalt concrete (PAC) is typically used as a paving material for porous asphalt pavement in rainy areas due to its abundant interconnected pores structure. Not all interconnected pores in PAC are valid for permeability, mainly influenced by the composition of aggregate gradation. The main purpose of this paper is to investigate the effect of aggregate gradation on pores structure distribution in PAC by X-ray computed tomography (CT) system and digital image processing (DIP) techniques. The distributions of porosity, number and average equivalent diameter of air voids in middle part are much more evenly compared to the both ends in PAC specimens, accounting for about 70 % of the total of specimen height. The average equivalent diameter of interconnected air voids mainly ranges from 0.5 mm to 5 mm in PAC, accounting for about 80 % of the total numbers. For PAC with similar porosity, the larger the normal maximum aggregate size (NMAS), the less the number and the larger the average equivalent diameter of air voids (interconnected air voids), the smaller the difference between the interconnected porosity and porosity. For PAC with same NMAS, as the porosity increase, the number and average equivalent diameter of air voids (interconnected air voids) are respectively decreased and increased gradually, the difference between the interconnected porosity and porosity is also showed a decreasing trend. And then, the correlated equation is established among porosity, interconnected porosity and the composition of aggregate gradation. The distribution of air voids (interconnected air voids) size could be well described by the two-parameter Weibull model, and the relationships are explored and developed between Weibull model parameters and the composition of aggregate gradation.

Photomonitoring as a Tool for Monitoring Landslides: A Technology within Everyone’s Reach

Landslides pose significant threats to human lives and infrastructure, making accurate monitoring essential for understanding and preventing these events. Photomonitoring, utilizing optical/multispectral sensors and digital image processing techniques, has emerged as a valuable tool for studying and monitoring landslide deformation processes. This article explores the application of photomonitoring in landslide studies, presenting three diverse case studies showcasing its efficacy and versatility. The technique allows for continuous, automated, and real-time monitoring of landslide events, providing valuable insights into displacement patterns and deformation trends. To enhance its usability, the software IRIS was developed to analyze data acquired from various platforms and sensors. This innovative solution promises to improve landslide management, contributing to better comprehension, prevention, and mitigation strategies, ultimately ensuring the safety of communities and infrastructure in landslide-prone regions.

An investigation on enhancing the bonding properties of 3D printed concrete permanent formwork and post-casted concrete

Employing 3D-printed permanent formwork (3DPF) technology for rapidly manufacturing prefabricated components constructed with reinforced concrete represents a promising application of additive manufacturing technology in load-bearing constructions. Ensuring efficient bonding between 3DPF and post-casted concrete (PCC) is a prerequisite for the widespread adoption of this technology. This research aims to enhance the 3DPF-PCC interface through: physical (groove), chemical (cement paste) and composite methods. The interfacial bond strength was quantitatively analysed by splitting tensile strength and shear strength. X-ray computed tomography scanning was utilized for the quantitative characterization of pore structures. Digital image processing techniques were employed to monitor crack development during splitting tensile tests. The mechanism for strengthening the shear strength of the grooved interface was elucidated using a finite element model, and a modified formula for calculating the shear strength of the 3DPF-PCC grooved interface was proposed. The physical method improves shear strength by increasing interlocking structures significantly. The composite method weakens mechanical interlocking structures, increases interface porosity, and adversely affects interface bonding strength. It is recommended that future engineering applications adopt the physical process to improve mechanical interlocking structures and ensure interface bonding strength.

Derivation of elastic and inelastic characteristics of non-periodic masonry using homogenization techniques and micro-modelling approaches

The present study is aimed to develop an ad hoc four-steps procedure, based on the use of Digital Image Processing (DIP) techniques, homogenization methods and micro-modelling approaches, able to provide an effective tool for characterizing the mechanical properties of non-periodic masonry. More in detail, after creating, through a DIP technique and automated procedures, a finite element mesh from the Red-Green-Blue (RGB) image of a real masonry wall with non-periodic texture (Step 1 and Step 2), a homogenization method, which considers the properties of each masonry constituent (stone units and mortar joints), is used to derive the main elastic characteristics of a homogeneous continuum equivalent to the random masonry (Step 3). Specifically, this estimate can be achieved following the test-windows method based on the use of least-sized partitions subjected to boundary conditions in terms of displacements or stresses until a chosen convergence criterion is fulfilled. The non-linear response is then accomplished by means of a micro-modelling approach (Step 4). To this end, a three-dimensional finite element (FE) analysis can be therefore developed to characterize the main inelastic material parameters of the random masonry. Lastly, as a benchmark of the method, the proposed procedure has been validated against the laboratory outcomes obtained from a previous experimental campaign on non-periodic masonry walls.