A comprehensive assessment of image processing variability in pore structural investigations: Conventional thresholding vs. machine learning approaches

The mechanical properties of the carpet, such as dimensional stability, bending stiffness, handle and creeping on the surface during use, have a direct relationship with the amount of resin applied to the back of the carpet in the sizing process. In today’s factories, the optimal amount of resin and the mechanical quality of the carpet are controlled by the operator touching the carpet on the machine carpet finishing line or manually while rolling the carpet. Proposed in this paper is an automatic method based on the evaluation of the bending stiffness of the sized carpet that uses digital image processing and machine learning to measure the optimal amount of size concentration and control this index. For this purpose, during the final stage of carpet production, the carpet is folded in the middle, and two edges of the carpet are placed on top of each other. A side view image is then taken of the carpet. Using edge detection methods, the edges of the carpet are identified, and different features, such as the average, maximum and minimum statistics for the curve and contour angles, are then extracted. Different conventional machine learning approaches, such as KNN, CART and SVM, are applied. To evaluate the proposed method, a dataset containing 220 different images is used in a 10-fold cross-validation scheme. Different performance measures resulting from the evaluations demonstrate the effectiveness and applicability of the method.

Hyperspectral imaging (HSI) is a technology able to measure information about the spectral reflectance or transmission of light from the surface. The spectral data, usually within the ultraviolet and infrared regions of the electromagnetic spectrum, provide information about the interaction between light and different materials within the image. This fact enables the identification of different materials based on such spectral information. In recent years, this technology is being actively explored for clinical applications. One of the most relevant challenges in medical HSI is the information extraction, where image processing methods are used to extract useful information for disease detection and diagnosis. In this chapter, we provide an overview of the information extraction techniques for HSI. First, we introduce the background of HSI, and the main motivations of its usage for medical applications. Second, we present information extraction techniques based on both light propagation models within tissue and machine learning approaches. Then, we survey the usage of such information extraction techniques in HSI biomedical research applications. Finally, we discuss the main advantages and disadvantages of the most commonly used image processing approaches and the current challenges in HSI information extraction techniques in clinical applications.

We introduced the image processing application to identify fracture and calculate fracture porosity based on the image logging for the gas-bearing shale. Shale gas is an unconventional gas resource and has been paid more attention in recent years. The pore structure of shale is very complicated, where fracture is the main flowing channel. The conventional logging and the imaging logging offer the abundant information for formation evaluation in downhole. The dual laterolog logging is used to identify fracture, but difficult to get accurate fracture porosity. The imaging logging could directly characterize fracture in the borehole and easily estimate fracture porosity with images processing method. The image logging processing with the mathematical morphology to calculate the fracture porosity was discussed in the paper. A typical shale gas well Jiaoye1 from Jiaoshiba area of Chongqing City in Sichuan Basin was presented to compare the calculation result of the two methods. The results shows that both the dual laterolog logging and the image logging could identify borehole fracture and calculate fracture porosity, where the dual laterolog logging has relatively large uncertainty. The advantage of the imaging logging clearly indicates borehole fracture, but the image processing method should be improved.

Chapter 2 - New Image Processing Methods for Advanced Metallization in Micro- and Nano-Electronics

BIB-SEM characterization of pore space morphology and distribution in postmature to overmature samples from the Haynesville and Bossier Shales

Global sensor feedback for automatic nanohandling inside a scanning electron microscope

Predictive selection rule of favourable image processing methods for X-ray micro-computed tomography images of tablets

Image processing methods have become consistently used approaches in a wide variety of applications with modern technology devices. Image classification and segmentation is a common topic in computer vision as well as a backbone and focal point in image processing approaches. Biometric and biomedical image processing are two of the most common examples of image processing applications that we have seen over the past two decades. in medicine, there is a great need for modern imaging technology algorithms that can be used to detect the internal organs of the human body in the process of disease diagnosis. To this end, researchers are working every day to develop new methods or improve existing methods that will help in efforts to improve human life and health. in this study, a comparative study was conducted to evaluate the performance of different types of machine learning classification algorithms on brain tumor images. According to the result obtained, the performance of the models differs in the accuracy of their classification capabilities. Different performance measurements are used during the evaluation and interpretation of the results and the results obtained are presented in the comparison table in the results section. Six classification models are used, which are mainly used in the field of Machine Learning (ML) and Artificial Intelligence (AI). Future studies may increase the comparison techniques by adding other classification and clustering techniques to study the effectiveness of each technique in the classification operation of medical images.

This paper provides an overview of automatic fabric fault detection approaches that have been developed in recent years. Fabric fault detection is very popular topic of automation moreover quality control is one of the important features in textile industry. The performance of the projected idea is evaluated by using different techniques of patterned fabric images with different types of common fabric defects. Moreover detection methods were also evaluated in real time using a model automation specification system. This research paper will be useful for both researchers and practitioners in the field of image processing and computer vision to understand the uniqueness of the different defect detection methods. The recognition receives a digital fabric image from the image acquisition device and transforms it to a binary image using the restoration and threshold methods. This research presents a technique that decreases physical exertion. This image processing method was performed using “MATLAB 7.10”. Therefore, this study uses a textile fault detector with a systematic vision approach for image processing.

In-situ monitoring of laser-based PBF via off-axis vision and image processing approaches

This study aimed to evaluate the impact of UVC (Ultraviolet C Radiation), detergent foam, and alcohol (70%) sterilization methods on the surface morphology of acrylonitrile-butadiene-styrene (ABS) specimens using a novel SEM (Scanning Electron Microscope) image processing approach. Twelve 3D-printed specimens were prepared, and five concentric circular regions of interest (ROIs) per specimen were analyzed. Three quantitative descriptors-defect area fraction, anisotropy ratio, and RMS (Root Mean Square) roughness-were extracted to assess surface alterations. To validate the image-based findings, EDX (Energy-Dispersive X-ray Spectroscopy) elemental analysis for carbon (C), nitrogen (N), and oxygen (O) was employed as a complementary and traditional benchmark technique. Statistical comparisons and p-value heat maps revealed strong convergence between SEM and EDX results. UVC sterilization consistently preserved surface morphology and elemental stability, showing the lowest defect fraction (p = 0.2684), balanced anisotropy (p = 0.02481), and minimal oxygen incorporation (O = 7.6). Foam sterilization produced intermediate effects, with significant anisotropy changes (p = 0.007456) and reduced nitrogen (19.6). Alcohol sterilization induced the most severe damage, characterized by high defect density, increased roughness, and elemental imbalance (N = 17.3, O = 13.9), confirming oxidative degradation. The convergence of SEM and EDX outcomes demonstrates that SEM image processing is a reliable novel method validated by traditional elemental analysis. Together, these approaches provide a robust framework for ranking sterilization efficacy, with UVC identified as the most favorable method, detergent foam as an acceptable alternative, and alcohol as the least effective due to its destabilizing effects.

Integrated digital image processing techniques and deep learning approaches for wheat stripe rust disease detection and grading

In this paper, an obstacle avoidance and target tracking method for both indoor and outdoor mobile robots in dynamic environment is presented, and it aims to enhance autonomous navigation capability of such robots. In the proposed method, image processing and machine-learning approaches are considered. Since obstacles have differences in color and texture and in order to identify non-navigable areas, a monocular onboard camera is used to capture the road lanes by dealing with an image processing technique. The position of the robot with respect to road lane center during navigation is calculated on the basis of a proposed fuzzy logic rules set. In order to provide fast and robust computation, the Haar cascade classifier-based machine-learning technique has been exploited to detect the different sizes and shapes of the obstacles faced by the robot during its movement from source to destination. The dynamic model of a four-wheel mobile robot is initially developed using bond graph theory and then, the proposed obstacle-avoidance strategy is applied. The effectiveness and performance of the proposed method are tested under various simulation and experimentation scenarios. The behavior of the mobile robot for detecting and avoiding static obstacle for single and double road lane change environment is analyzed and discussed.

Agriculture plays a foremost role in countries growth. The physical recognition of disease in the plant is more timeconsuming and necessity of expert labor is high. One of the most vital aspect in agriculture field is plant disease that reduces quality andquantity of agricultural crops. The machine learning approaches can easily recognize these diseases compared to physical method. So the machine learning techniques in addition toimage processing is used to identify diseased leaf. These methods will help in recognizing plant diseases thus increasing the yield of plants. This paper concentrates on the previous research work that used the characteristics of machine learning techniques in addition to image processing. It describes the various plant disease types, image processing methods and also various techniques of plant disease systems are analyzed with accuracy. Finally, the various challenges in the recognition of plant leaf diseases are identified and listed.

How shale reservoirs and gas contents are affected by the pore structure of shale is very important. Low-temperature nitrogen isothermal adsorption experiments were conducted by us to investigate the pore structure of the Dalong Formation shale. We measured the specific surface area and fractal dimension of the pores and also considered the mineral fraction and organic matter content of the rock. The results show that the Dalong Formation shale contains a lot of organic carbon, with a total organic carbon (TOC) value between 1.20 and 10.82% (mean: 5.02%). Quartz and clay minerals are the main components of the shale, with quartz making up 40.30 to 85.60% (mean: 67.21%) and clay minerals making up 9.20 to 34.10% (mean: 20.26%) of the shale. Most of the pore space in the shale of the Dalong Formation is formed by intragranular and intergranular pores, organic matter pores, and some microfissures. The pore structure is complex, with parallel-plate and ink-bottle pores being the most common types. Most of the pores are 0-2 or 2-5 nm in size. D1 and D2 are the fractal dimensions, with averages of 2.66 and 2.81, respectively. D1 can range from 2.55 to 2.78, while D2 can range from 2.66 to 2.94. The TOC content, mineral composition, and pore structure characteristics determine the fractal dimension. Higher levels of the TOC content, quartz mineral content, and specific pore surface area result in a higher fractal dimension, while higher levels of feldspar content result in a lower one. There is no apparent correlation to clay minerals or other mineral compositions.