Digital Image Processing Methods Research Articles

Automatic Defects Recognition of Lap Joint of Unequal Thickness Based on X-Ray Image Processing

It is difficult to automatically recognize defects using digital image processing methods in X-ray radiographs of lap joints made from plates of unequal thickness. The continuous change in the wall thickness of the lap joint workpiece causes very different gray levels in an X-ray background image. Furthermore, due to the shape and fixturing of the workpiece, the distribution of the weld seam in the radiograph is not vertical which results in an angle between the weld seam and the vertical direction. This makes automatic defect detection and localization difficult. In this paper, a method of X-ray image correction based on invariant moments is presented to solve the problem. In addition, a novel background removal method based on image processing is introduced to reduce the difficulty of defect recognition caused by variations in grayscale. At the same time, an automatic defect detection method combining image noise suppression, image segmentation, and mathematical morphology is adopted. The results show that the proposed method can effectively recognize the gas pores in an automatic welded lap joint of unequal thickness, making it suitable for automatic detection.

A Multi-aperture Coaxial Projector Balancing Shadow Suppression and Deblurring.

This paper proposes a projection system that optically removes the cast shadow in projection mapping. Specifically, we realize the large-aperture (LA) projection using a large-format Fresnel lens to suppress cast shadows by condensing the projection light from a wide viewing angle. However, the resolution and contrast of the projected results are significantly degraded by defocus blur, veiling glare, and stray light caused by the aberration of an LA Fresnel lens. To solve the technical problems, we employ two different approaches: optical and digital image processing methods. First, we introduce a residual projector with a typical aperture lens on the same optical axis as the LA projector, projecting the residual (i.e., high-frequency) components attenuated in the LA projection. These projectors play different roles in shadow suppression and blur compensation, both achieved by projecting simultaneously. Secondly, we optimize the pair of projection images that can balance the shadow suppression and deblurring performance of our projection system. We implemented a proof-of-concept prototype and validated the above-mentioned techniques through projection experiments and a user study.

Measuring pore sizes of nonwoven geotextiles by X-ray CT images: a comparative evaluation

This paper focuses on evaluating the pore sizes of four nonwoven geotextile specimens with different pore size distribution techniques. The paper introduces a bubble analysis technique to find the two-dimensional (2D) pore size distribution of geotextile specimens. A new method is also introduced to determine the three-dimensional (3D) constriction sizes of nonwoven geotextiles from X-ray CT images. The digital image concept and image processing methods for the 2D image analysis and 3D constriction size measurement of geotextile specimens are explained. Finally, the paper compares the 3D constriction sizes with those measured from 2D image analysis, mercury intrusion porosimetry, manufacturer-reported opening size values based on the wet sieving method, and pore sizes calculated from theoretical equations. The results show that the largest pore opening sizes measured from the 3D constriction size method are in good agreement with the theoretical equations. The values measured from the wet sieving method were found to be the smallest, indicating the limitations of the wet sieving method to determine the largest pore opening size of nonwoven geotextiles. As it is the constriction size which must control filtration behaviour, the 3D constriction size method is recommended for assessing the reference porometry.

The Quantitative Evaluation of the Cell Structure Uniformity of Microcellular TPU with Low Porosity via a Digital Image Processing Method.

The cell structure uniformity of microcellular polymers significantly impacts material performance, especially for low-porosity microcellular TPU used in chip polishing. The distribution of the cell structure of polishing pads directly affects the removal rate and process repeatability. Despite its importance, no quantitative method for evaluating cell structure uniformity has been reported in the literature. In this study, a digital image processing method that involves morphological operations of scanning electron microscopy (SEM) images, binarization, and cell localization, and the statistical evaluation of cell structure parameters was established to evaluate cell structure uniformity. A quantitative metric, the cell structure uniformity index (CUI), was calculated based on cell structure indices, incorporating the cell size index (Ud), the cell number index (Un), and the cell local spacing index (Ur). By establishing an ideal model and analyzing representative SEM images, the effectiveness and efficiency of the method for evaluating cell structure uniformity of microcellular TPU were successfully validated. The results demonstrated that low-porosity TPU foams exhibited relatively low cell structure uniformity compared to the ideal model. The heterogeneous nucleation process in TPU caused non-uniform cell structures due to the temporal and spatial non-homogeneities during the early cell nucleation process. As the cells grew, they merged and reduced the distance between them, resulting in improved cell structure uniformity.

Research on the Recognition and Characterization of Fractures in Coal Rock Based on CT Scanning

Abstract Coal rock fractures play a vital role as key channels for gas migration and storage in the exploration and development of coalbed methane. The characteristics of these fractures, such as porosity distribution, specific surface area, and connectivity, directly impact the adsorption, diffusion, and permeability behaviors of coal reservoirs. Therefore, a detailed analysis of coal rock fracture characteristics is vital in assessing the extractability of coalbed methane and during its exploration and development process. Currently, techniques like imaging logging, seismic detection, and micro-CT are employed for characterizing and studying fractures at various scales. Among these, high-resolution non-destructive CT scanning technology, by constructing three-dimensional data models of core samples, enables a quantitative analysis of fracture distribution features and size parameters. Traditional digital image processing methods, such as threshold segmentation and binary segmentation, though advantageous in computational speed, have limitations in the accuracy of fracture identification. With the advancement of artificial intelligence technology, deep learning-based image processing techniques have increasingly become significant tools for fracture detection due to their powerful feature extraction capabilities. This study conducted micrometer-level CT scanning experiments on coal rock samples, using CT image processing technology to construct a digitalized coal rock core model. Deep learning methods were applied for precise fracture identification, establishing an appropriate deep learning architecture and optimized parameters for coal rock fracture recognition. Furthermore, this paper provides a detailed quantitative characterization of the precisely identified fractures, offering robust technical support for the exploration and development of coalbed methane. The high-resolution non-destructive CT scanning technology and three-dimensional fracture network reconstruction method used in this study have been proven to be effective tools for investigating the micro-features of rocks, enabling the three-dimensional visualization and detailed characterization of rock microstructures.

AIRBORNE LASER SCANNER AS A DATA SOURCE FOR BUILDING SELECTED ELEMENTS OF AN INTELLIGENT DATABASE FOR TRANSPORTATION

In this study, the main objective was to detect the road network and key road infrastructure elements based on airborne laser scanning data. The study included identification of the road network and determination of its axes using three independent methods, as well as detection of horizontal signs such as pedestrian crossings. The analysis process was based mainly on digital image processing methods, based solely on lidar data, without using information from other sources. The results of the analysis showed that the use of lidar data provides a fast and effective method for continuously updating information on road infrastructure and expanding the transportation database. This potentially opens the door to effectively updating relevant data in the area of transportation infrastructure.

Morphological variability of Cyprinus Carpio Linnaeus, 1758 in water bodies of the Balkash-Alakol basin

The article presents the results of investigating the morphological variability of carp (Cyprinus carpio Linnaeus, 1758) in three large reservoirs of the Balkash-Alakol Basin – Lake Balkash, Lake Alakol, and Kapshagay Reservoir. Morphological differences in several features (counting and plasticity) were found in three carp samples. The study included the examination of 24 plastic and 14 counting features. The method of digital image processing (Morpho J) was applied to analyze the differences of the target fish species specimens by body shape. The application of the principal component analysis (PCA) method allowed determining the main loadings on the studied morphological traits of carp. The statistically reliable differences revealed allow to confirm the formation of morphological changes in carp caused by the duration of adaptive radiation, environmental factors of water bodies and annual artificial stocking of young fish.

Speckle reduction in digital holography with Non-local means filter based on the structural similarity

Speckle noise limits the application of digital holography across various fields. This paper proposes a Non-local means filter method to suppress speckle noise by determining the weight of each traversed pixel based on the structural similarity between image blocks centered on the target and traversed pixels. Experimental results show that, compared to other typical digital image processing methods, this method can significantly reduce the speckle noise and exhibits a clear advantage across various metrics. These results indicate that the proposed method holds significant development potential in the field of speckle noise reduction.

Detection and Assessment of Hull Plate Corrosion Damage Based on Image Recognition Techniques

Corrosion damage can lead to a decrease in the ultimate strength and carrying capacity of ship structures, and even result in buckling or fracture. With the rapid development of deep learning, image recognition processing, and convolutional neural networks (CNN) are playing an important role in the field of corrosion damage detection and assessment. In this paper, corrosion damage images are obtained by taking photos of test pieces of accelerated corrosion tests, and a corrosion damage database is established to provide data for the establishment of the subsequent image corrosion damage level dataset and the training of the CNN model. Digital image processing methods and unsupervised learning clustering algorithms are used to identify and process corrosion images and obtain corrosion parameters. Based on the corrosion parameters, the images are classified into different corrosion damage levels to establish a corrosion damage dataset with corrosion damage level labels. This dataset is used to train a CNN model and establish a corrosion damage level assessment interface. By inputting corrosion damage images, the corrosion damage level assessment results can be obtained.

Advancing Microplastic Detection Technology through Digital Image Processing, Fractal Analysis, and Polynomial Approximation Methods

Advancing Microplastic Detection Technology through Digital Image Processing, Fractal Analysis, and Polynomial Approximation Methods

Effectiveness of an X-ray shielding sheet with lower shielding ability to enable both bone mineral density determination and morphological diagnosis

Bone Mineral Density (BMD) can be determined by applying the Digital Image Processing (DIP) method using medical X-ray diagnosis. Although only the second metacarpal bone is analyzed in this approach, other parts of the body are exposed to X-ray radiation. We here propose a novel procedure in which parts of the hand surrounding the area of interest are shielded with an X-ray shielding sheet having low shielding performance. In our procedure, the main diagnostic area is not shielded, and other areas are covered with an X-ray shielding sheet with a low shielding performance. The sheet was fabricated by embedding Bi2O3 particles in resin sheet. We assessed the clinical performance of this method using three types of hand phantoms and conventional diagnostic X-ray equipment. The dose reduction for the entire hand region was evaluated by the Dose Area Product (DAPHand), which was measured with a small dosimeter, and the hand area was determined from the X-ray image. The X-ray image of the second metacarpal bone is affected by the contribution of X-rays that penetrate the object of interest and are scattered in other areas of the hand. Because our X-ray shielding sheet suppressed the generation of scattered X-rays, the pixel value of the second metacarpal bone and corresponding BMD value are varied. To address this issue, we developed a correction algorithm. We found that the X-ray shields with Dose Reduction Factor (DRF) values of 40–60% were appropriate for our methodology. Our method was estimated to have a percentage uncertainty of approximately 5% for the derivation of BMD values. Morphological information of the hand and bones could thus be clearly observed. We verified that both morphological diagnosis and quantitative determination of BMD are possible when DIP procedure is conducted using our shield.

A comparison among a fuzzy algorithm for image rescaling with other methods of digital image processing

The aim of this paper is to compare the fuzzy-type algorithm for image rescaling introduced by Jurio et al., 2011, quoted in the list of references, with some other existing algorithms such as the classical bicubic algorithm and the sampling Kantorovich (SK) one. Note that the SK algorithm is a recent tool for image rescaling and enhancement that has been revealed to be useful in several applications to real world problems, while the bicubic algorithm is widely known in the literature. A comparison among the abovementioned algorithms (all implemented in the MatLab programming language) was performed in terms of suitable similarity indices such as the Peak-Signal-to-Noise-Ratio (PSNR) and the likelihood index $S$.

Formation of a panoramic image of the inner surface of the pipe

Background. Visual non-destructive testing of the inner surface of pipes is an important aspect in their production and operation. A defect detected and corrected in a timely manner can significantly reduce the number of defects in production and prevent various emergency incidents during operation. Formation of a complete panoramic image of the inner surface of pipes suitable for quality analysis is an urgent and sought-after task that can be solved using computer vision systems. Aim. This work is the research and development of television methods for forming a complete panoramic image of the inner surface of a pipe, which can be analyzed to search for defects. Methods. To form a cylindrical panoramic image, mathematical models for the formation of an equidistant projection of spherical images obtained using a fisheye lens were used. For high-quality stitching of the resulting frames, digital image processing methods were used, including brightness and contrast transformations, and searching for special points using the MSER algorithm. Theoretical results are verified by full-scale modeling. Results. The result of this work is an algorithm for stitching frames of a video sequence generated by a television camera with a fisheye optical system, uniformly moved along the longitudinal axis of the pipe, into a single panoramic image of the internal surface. Conclusion. The algorithm ensures the formation of a high-quality image of a full panorama of the inner surface of the pipes with the absence of brightness artifacts.

Recognition of Intergranular Corrosion in AISI 304 Stainless Steel by Integrating a Multilayer Perceptron Artificial Neural Network and Metallographic Image Processing

The correct management of operations in thermoelectric plants is based on the continuous evaluation of the structural integrity of its components, among which there are elements made of stainless steel that perform water conduction functions at elevated temperatures. The working conditions generate progressive wear that must be monitored from the perspective of the microstructure of the material. When AISI 304 stainless steel is subjected to a temperature range between 450 and 850 °C, it is susceptible to intergranular corrosion. This phenomenon, known as sensitization, causes the material to lose strength and generates different patterns in its microstructure. This research analyzes three different patterns present in the microstructure of stainless steel, which manifest themselves through the following characteristics: the absence of intergranular corrosion, the presence of intergranular corrosion, and the precipitation of chromium carbides. This article shows the development of a methodology capable of recognizing the corrosion patterns generated in stainless steel with an accuracy of 98%, through the integration of a multilayer perceptron neural network and the following digital image processing methods: phase congruence and a gray-level co-occurrence matrix. In this way, an automatic procedure for the analysis of the intergranular corrosion present in AISI 304 stainless steel using artificial intelligence is proposed.

Wound Tissue Segmentation and Classification Using U-Net and Random Forest

Analysing wound tissue is a crucial research field for assessing the progression of wound healing. Wounds exhibit certain attributes concerning colour and texture, although these features can vary among different wound images. Research in this field serves multiple purposes, including confirming the presence of chronic wounds, identifying infected wounds, determining the origin of the wound and addressing other factors that classify and characterise various types of wounds. Wounds pose a substantial health concern. Currently, clinicians and nurses mainly evaluate the healing status of wounds based on visual examination. This paper presents an outline of digital image processing and traditional machine learning methods for the tissue analysis of chronic wound images. Here, we propose a novel wound tissue analysis system that consists of wound image pre-processing, wound area segmentation and wound analysis by tissue segmentation. The wound area is extracted using a simple U-Net segmentation model. Granulation, slough and necrotic tissues are the three primary forms of wound tissues. The [Formula: see text]-means clustering technique is employed to assign labels to tissues. Within the wound boundary, the tissue classification is performed by applying the Random Forest classification algorithm. Both segmentation (U-Net) and classification (Random Forest) models are trained, and the segmentation gives 99% accuracy, and the classification model gives 99.21% accuracy.

COMPARATIVE ANALYSIS OF SPECTRAL ANOMALIES DETECTION METHODS ON IMAGES FROM ON-BOARD REMOTE SENSING SYSTEMS

The subject matter of the article is methods of detecting spectral anomalies on images from remote sensing systems. The goal is to conduct a comparative analysis of methods for detecting spectral anomalies on images from remote sensing systems. The tasks are: analysis of the main methods of detecting spectral anomalies on images from remote sensing systems; processing of images from remote sensing systems using basic methods of detecting spectral anomalies; comparative assessment of the quality of methods for detecting spectral anomalies on images from remote monitoring systems. The methods used are: methods of digital image processing, mathematical apparatus of matrix theory, methods of mathematical modeling, methods of optimization theory, analytical and empirical methods of image comparison. The following results are obtained. The main methods of detecting spectral anomalies on images from remote sensing systems were analyzed. Processing of images from remote sensing systems using the basic methods of detecting spectral anomalies was carried out. A comparative assessment of the quality of methods for detecting spectral anomalies on images from remote monitoring systems was carried out. Conclusions. The spectral difference of the considered methods is revealed by the value of information indicators - Euclidean distance, Mahalanobis distance, brightness contrast, and Kullback-Leibler information divergence. Mathematical modeling of the considered methods of detecting spectral anomalies of images with a relatively “simple” and complicated background was carried out. It was established that when searching for a spectral anomaly on an image with a complicated background, the method based on the Kullback-Leibler divergence can be more effective than the other considered methods, but is not optimal. When determining several areas of the image with high divergence indicators, they should be additionally investigated using the specified methods in order to more accurately determine the position of the spectral anomaly.

Detection of Throat Disorders Based on Thermal Image Using Digital Image Processing Methods

Throat disorders are often considered trivial for some people, but if they are not treated immediately they can result in more severe conditions and require a longer time to cure this disorder. Objective, safe and comfortable detection of throat disorders is important because throat disorders are an indication of inflammation which, if not treated immediately, can have negative consequences. This research aims to detect throat disorders based on thermal images using digital image processing methods. Image capture was carried out with the same color pallete range on the camera, namely 33°C-38°C. The image obtained is then cropped in the ROI, then the image is threshold with a gray degree of 190. Pixels that have a gray degree above 190 are converted to white, while those below the threshold are converted to black. Next, the percentage of each white and black area is calculated compared to the total ROI area. If the percentage of white area is greater than 38% compared to the area of ​​the throat then it is identified as having a throat disorder, whereas if the percentage of white is less than 38% then it is identified as not having a throat disorder. The detection program created provides an accuracy of 87.5% on sample data of 8 test data.

Automated Defect Recognition Using Spline Interpolation

Existing infrastructure systems are aged and deteriorated rapidly, state agencies started searching for more advanced way to maintain their valuable assets to the acceptable level. One of them is the application of digital image processing. This problem proposes a digital image processing method to assess a steel bridge coating surface. The image processing method was developed based on B-Spline interpolation and can be used to recognizing the existence of bridge coating rust defects. An automated defect recognition method can make a decision whether a given digitized image contains defects by image comparison. Key Words:B-Spline interpolation, Digital Image Processing, Automated defect recognition method, Image comparision

Fluidization characteristics of loaded vibrating fluidized bed and dewatering and deashing effect of moist fine-grained coal

ABSTRACT The influence of a thermal vibrating fluidized bed on the dewatering and deashing effect of moist fine-grained coal was investigated by digital image processing and signal analysis methods. Comparative analysis results of the pressure signals of a loaded vibrating fluidized bed indicated that high or low gas velocity and strong or weak vibration conditions easily caused the formation of numerous irregular bubbles and contributed to violent fluctuations in the bed. An interaction between gas velocity and vibration energy was found, with vibration energy being the dominant factor influencing the bubble behavior at low gas velocities. Moreover, at high gas velocities, the advantages arising from vibrations were weakened. Under the condition of f = 20 Hz, A = 2 mm, v = 18 cm⋅s−1, the contact efficiency between the gas – solid two phases was higher, and the pressure fluctuation of the bed became more stable. Under this condition, the ash content of clean coal and the moisture removal rate were 11.76% and 83.54%, respectively. Finally, comparison and analysis of the influence of different parameters on the calorific value of clean coal revealed that the influence of each parameter on heat generation of the selected product was found to be in the following order: f > A > V > T.

Enchancing Lung Disease Classification through K-Means Clustering, Chan-Vese Segmentation, and Canny Edge Detection on X-Ray Segmented Images

The lungs are one of the vital organs in the human body. Not only play a role in the respiratory system, the lungs are also responsible for the human circulatory system. Supporting examinations can also facilitate medical workers in determining the diagnosis. Usually a lung examination is complemented by a chest X-ray examination procedure. This examination aims to see directly and assess the severity of lung conditions. With current technological advances, image analysis can be done easily. Through digital image processing methods, information can be obtained from images that can be used for analysis as a support for diagnoses in the world of health. Image segmentation is a method in which digital images are divided into several segments or subgroups based on the characteristics of the pixels in the image. In this study, clustering with the K-Means method will be carried out on the results of segmentation of x-ray images of lung diseases, namely Covid-19, Tuberculosis, and Pneumonia. The segmentation method that will be implemented is the Chan-Vese Method and the Canny Edge Detection Method. This research shows that the results of the accuracy of applying the K-Means Clustering method to Chan-Vese and Canny Edge-Based Image Segmentation are 80%.