Image Processing Methods Research Articles

Local maximum synchrosqueezing adaptive transformation for cross-instantaneous frequencies analysis

Abstract To overcome the shortcomings of existing time-frequency (TF) analysis (TFA) methods in analyzing signals containing cross-instantaneous frequencies (IFs), this paper proposes an adaptive TFA technique combined with image processing methods based on local maximum synchrosqueezing transform. The core idea of the proposed algorithm is to localize the filtering of signals containing several different IF components using kernel functions containing several different directions, respectively, to achieve energy separation at the crossing frequencies. In turn, the local maximum synchrosqueezing transform is used to rearrange the TF energy to the true IF ridges of the signal to improve the TF energy concentration. Simulation data demonstrates that the proposed algorithm has higher energy aggregation and better noise immunity, especially for signals with cross-IFs. Applying the proposed method to animal acoustic and radar wave signals of pedestrians can accurately describe the differences in the frequency change patterns and the temporal distribution of energy in the signals, thereby providing a judgment basis for effectively identifying and classifying the signals.

Influence of Spatial Scale Effect on UAV Remote Sensing Accuracy in Identifying Chinese Cabbage (Brassica rapa subsp. Pekinensis) Plants

The exploration of the impact of different spatial scales on the low-altitude remote sensing identification of Chinese cabbage (Brassica rapa subsp. Pekinensis) plants offers important theoretical reference value in balancing the accuracy of plant identification with work efficiency. This study focuses on Chinese cabbage plants during the rosette stage; RGB images were obtained by drones at different flight heights (20 m, 30 m, 40 m, 50 m, 60 m, and 70 m). Spectral sampling analysis was conducted on different ground backgrounds to assess their separability. Based on the four commonly used vegetation indices for crop recognition, the Excess Green Index (ExG), Red Green Ratio Index (RGRI), Green Leaf Index (GLI), and Excess Green Minus Excess Red Index (ExG-ExR), the optimal index was selected for extraction. Image processing methods such as frequency domain filtering, threshold segmentation, and morphological filtering were used to reduce the impact of weed and mulch noise on recognition accuracy. The recognition results were vectorized and combined with field data for the statistical verification of accuracy. The research results show that (1) the ExG can effectively distinguish between soil, mulch, and Chinese cabbage plants; (2) images of different spatial resolutions differ in the optimal type of frequency domain filtering and convolution kernel size, and the threshold segmentation effect also varies; (3) as the spatial resolution of the imagery decreases, the optimal window size for morphological filtering also decreases, accordingly; and (4) at a flight height of 30 m to 50 m, the recognition effect is the best, achieving a balance between recognition accuracy and coverage efficiency. The method proposed in this paper is beneficial for agricultural growers and managers in carrying out precision planting management and planting structure optimization analysis and can aid in the timely adjustment of planting density or layout to improve land use efficiency and optimize resource utilization.

Polarization-multiplexed zoom Moiré metalens for edge-enhanced imaging

Optical image processing with high operational efficiency has been applied as a pre-processing imaging system for image recognition. Edge-enhanced imaging as a high-efficiency optical image processing method is of great significance for feature extraction and target recognition. However, the edge-enhanced imaging system based on the 4F system and the spatial filter transforms mainly work under coherent light illumination conditions, without continuously zooming to track the spatial position of the target. Here, we demonstrate a polarization-multiplexed zoom Moiré metalens for edge-enhanced imaging under incoherent light illumination. Metalens is designed to generate polarization-dependent optical transfer functions that produce edge-enhanced images with a resolution of 1.2 µm by digital subtraction. Furthermore, continuous zoom at the range of 1-2× is realized by constructing a Moiré metalens composed of cascaded metasurfaces. The cascaded metasurfaces consist of two center-aligned dielectric metasurfaces, each with a Moiré phase sensitive to the rotation angle. By rotating the metasurface, the phase profile of the cascaded metasurfaces changes, and the effect of continuous zoom is realized. The focal length can be actively changed from 38 µm to 77 µm with the focusing efficiency of 50.3%. This metalens can be applied to machine vision, microscopic imaging, and promotes the development of multi-functional integrated optical systems.

Multi-scale flow atomization characteristics of Jatropha biodiesel swirl liquid film breakup

The characteristics of the spray and droplets produced by liquid film breakup are crucial for understanding the atomization process in industrial furnace atomizers. This study employed high-speed camera technology to capture images of Jatropha biodiesel (JB) spray at various pressures and Ohnesorge numbers (Oh). Image processing methods were employed to analyze the evolution morphology and proper orthogonal decomposition (POD) of fuel swirl spray, revealing the instability, breakup length, spray cone angle, fractal characteristics of the liquid film breakup zone, and droplet distribution characteristics. The results indicated that the JB jet evolution progressed through stages: cylindrical jet, torsion liquid film, open swirl, complete swirl, and fully developed mode. The evolution and disintegration of the liquid film exhibited a complex structure with ligaments, perforations, and droplet separation. Flow disturbances induced the Klystron effect, characterizing microscopic droplet motion. As spray pressure increased, the growth rate of the disturbance wave increased, the breakup length decreased, the atomization cone angle enlarged, and the fractal dimension (FD) of the liquid film breakup zone increased. The droplet size distribution followed a log-normal distribution, with a substantial increase in the number of small droplets as injection pressure increased. This study provides valuable insights into the multi-scale flow atomization of biodiesel in industrial furnace, and is of great significance for the design, operation, and optimization of spraying systems in various industrial applications.

Attention-Guided Residual U-Net with SE Connection and ASPP for Watershed-Based Cell Segmentation in Microscopy Images.

Time-lapse microscopy imaging is a crucial technique in biomedical studies for observing cellular behavior over time, providing essential data on cell numbers, sizes, shapes, and interactions. Manual analysis of hundreds or thousands of cells is impractical, necessitating the development of automated cell segmentation approaches. Traditional image processing methods have made significant progress in this area, but the advent of deep learning methods, particularly those using U-Net-based networks, has further enhanced performance in medical and microscopy image segmentation. However, challenges remain, particularly in accurately segmenting touching cells in images with low signal-to-noise ratios. Existing methods often struggle with effectively integrating features across different levels of abstraction. This can lead to model confusion, particularly when important contextual information is lost or the features are not adequately distinguished. The challenge lies in appropriately combining these features to preserve critical details while ensuring robust and accurate segmentation. To address these issues, we propose a novel framework called RA-SE-ASPP-Net, which incorporates Residual Blocks, Attention Mechanism, Squeeze-and-Excitation connection, and Atrous Spatial Pyramid Pooling to achieve precise and robust cell segmentation. We evaluate our proposed architecture using an induced pluripotent stem cell reprogramming dataset, a challenging dataset that has received limited attention in this field. Additionally, we compare our model with different ablation experiments to demonstrate its robustness. The proposed architecture outperforms the baseline models in all evaluated metrics, providing the most accurate semantic segmentation results. Finally, we applied the watershed method to the semantic segmentation results to obtain precise segmentations with specific information for each cell.

Protecting Drawings at Production and Regime Facilities Using Neural Network Technology and DLP Systems

The existing methods of object image processing are analyzed. Problems of using the considered methods within the framework of DLP systems are considered. A new object image processing method was presented that allows processing of complex images. A metric of accuracy and completeness of plagiarism image detection was used to evaluate the quality of the developed method. Testing was carried out using image ranking to analyze the ability of the model to search for semantics. Comparative testing was carried out with the method based on raster neural models. The advantages and disadvantages of the developed method were highlighted, as well as options for further developmentAs a result of this work, a method for processing object images in native format has been developed. The main advantage of the developed method is the high rate of accuracy (87 %) and completeness (100 %). This study can be useful for further research in the field of vector image analysis. Also, the developed method can be applied as a tool similarly to raster methods of image processing (image search, classification, search for objects in the image).

A Machine Learning and Deep Learning-Based Account Code Classification Model for Sustainable Accounting Practices

Accounting account codes are created within a specific logic framework to systematically and accurately record a company’s financial transactions. Currently, accounting reports are processed manually, which increases the likelihood of errors and slows down the process. This study aims to use image processing techniques to predict cash codes in accounting reports, automate accounting processes, improve accuracy, and save time. Deep learning embeddings from Inception V3, SqueezeNet, VGG-19, VGG-16, Painters, and DeepLoc networks were utilized in the feature extraction phase. A total of six learning algorithms, namely Logistic Regression, Gradient Boosting, Neural Network, kNN, Naive Bayes, and Stochastic Gradient Descent were employed to classify the images. The highest accuracy rate of 99.2% was achieved with the combination of the Inception V3 feature extractor and the Neural Network classifier. The results demonstrate that image processing methods significantly reduce error rates in accounting records, accelerate processes, and support sustainable accounting practices. This indicates that image processing techniques have substantial potential to contribute to digital transformation in accounting, helping businesses achieve their sustainability goals.

Application of Different Image Processing Methods for Measuring Rock Fracture Structures under Various Confining Stresses

Fractures within granite may become channels for fluid flow and have a significant impact on the safety of waste storage. However, internal aperture variation under coupled conditions are usually difficult to grasp, and the inevitable differences between the measured data and the real fracture structure will lead to erroneous permeability predictions. In this study, two different CT (Computed Tomography) image processing methods are adopted to grasp internal fractures. Several CT images are extracted from different positions of a rock sample under different confining stresses. Two critical factors, i.e., aperture and the contact area ratio value within a single granite fracture sample, are investigated. Results show that aperture difference occurs under these two image processing methods. The contact area ratio value under two image processing methods has less than 1% difference without confining stress. However, there is larger than ten times difference when the confining stress increases to 3.0 MPa. Moreover, the edge detection method has the capability to obtain a relatively accurate internal fracture structure when confining pressure is applied to the rock sample. The analysis results provide a better approach to understanding practical rock fracture variations under various conditions.

The potential of federated learning for self-configuring medical object detection in heterogeneous data distributions

Medical Object Detection (MOD) is a clinically relevant image processing method that locates structures of interest in radiological image data at object-level using bounding boxes. High-performing MOD models necessitate large datasets accurately reflecting the feature distribution of the corresponding problem domain. However, strict privacy regulations protecting patient data often hinder data consolidation, negatively affecting the performance and generalization of MOD models. Federated Learning (FL) offers a solution by enabling model training while the data remain at its original source institution. While existing FL solutions for medical image classification and segmentation demonstrate promising performance, FL for MOD remains largely unexplored. Motivated by this lack of technical solutions, we present an open-source, self-configuring and task-agnostic federated MOD framework. It integrates the FL framework Flower with nnDetection, a state-of-the-art MOD framework and provides several FL aggregation strategies. Furthermore, we evaluate model performance by creating simulated Independent Identically Distributed (IID) and non-IID scenarios, utilizing the publicly available datasets. Additionally, a detailed analysis of the distributions and characteristics of these datasets offers insights into how they can impact performance. Our framework’s implementation demonstrates the feasibility of federated self-configuring MOD in non-IID scenarios and facilitates the development of MOD models trained on large distributed databases.

EHNet: Efficient Hybrid Network with Dual Attention for Image Deblurring

The motion of an object or camera platform makes the acquired image blurred. This degradation is a major reason to obtain a poor-quality image from an imaging sensor. Therefore, developing an efficient deep-learning-based image processing method to remove the blur artifact is desirable. Deep learning has recently demonstrated significant efficacy in image deblurring, primarily through convolutional neural networks (CNNs) and Transformers. However, the limited receptive fields of CNNs restrict their ability to capture long-range structural dependencies. In contrast, Transformers excel at modeling these dependencies, but they are computationally expensive for high-resolution inputs and lack the appropriate inductive bias. To overcome these challenges, we propose an Efficient Hybrid Network (EHNet) that employs CNN encoders for local feature extraction and Transformer decoders with a dual-attention module to capture spatial and channel-wise dependencies. This synergy facilitates the acquisition of rich contextual information for high-quality image deblurring. Additionally, we introduce the Simple Feature-Embedding Module (SFEM) to replace the pointwise and depthwise convolutions to generate simplified embedding features in the self-attention mechanism. This innovation substantially reduces computational complexity and memory usage while maintaining overall performance. Finally, through comprehensive experiments, our compact model yields promising quantitative and qualitative results for image deblurring on various benchmark datasets.

The collapse of modern exposures in the recording of X-RAY images in medicine

This article reviewed the methods and algorithms for processing and diagnosing X-ray images that are widely used in medicine today. In order to improve the implementation of deep learning in modern medicine and further improve the widespread use of HMLs, the method, algorithm and model of X-ray image processing using the Raspberry Pi device were analyzed.

IoT Based Precision Farming

This project focuses on leveraging drone images of the pests equipped with advanced sensors for pest detection in crops, combined with methods for image processing to identify diseases. The ultimate goal is to enhance crop health and productivity through timely and targeted pesticide application. Image processing techniques are used to detect signs of diseases and pests in the captured images. The use of machine learning CNN algorithm enhances the system’s ability to accurately classify and diagnose crop heath issues. Upon detection of pests, the IOT platform triggers a response mechanism to deploy a precision pesticide spraying system. This ensures targeted and localized treatment, reducing the overall use of pesticides and minimizing environmental impact. This project involves capturing images of pests using a camera, followed by processing these images to extract key features using various image processing techniques. The extracted features are analyzed using algorithms, primarily Convolutional Neural Networks (CNNs), to detect variations in color and other dominant characteristics in the images. By comparing these features across samples, the system can identify pests and plant diseases more efficiently. This approach aims to provide a quicker and more cost-effective solution for pest detection and disease management.

Fast autofocusing based on single-pixel moment detection

Traditional image processing-based autofocusing techniques require the acquisition, storage, and processing of large amounts of image sequences, constraining focusing speed and cost. Here we propose an autofocusing technique, which directly and exactly acquires the geometric moments of the target object in real time at different locations by means of a proper image modulation and detection by a single-pixel detector. An autofocusing criterion is then formulated using the central moments, and the fast acquisition of the focal point is achieved by searching for the position that minimizes the criterion. Theoretical analysis and experimental validation of the method are performed and the results show that the method can achieve fast and accurate autofocusing. The proposed method requires only three single-pixel detections for each focusing position of the target object to evaluate the focusing criterion without imaging the target object. The method does not require any active object-to-camera distance measurement. Comparing to local differential methods such as contrast or gradient measurement, our method is more stable to noise and requires very little data compared with the traditional image processing methods. It may find a wide range of potential applications and prospects, particularly in low-light imaging and near-infra imaging, where the level of noise is typically high.

Transformative insights: Image-based breast cancer detection and severity assessment through advanced AI techniques

Abstract In the realm of image-based breast cancer detection and severity assessment, this study delves into the revolutionary potential of sophisticated artificial intelligence (AI) techniques. By investigating image processing, machine learning (ML), and deep learning (DL), the research illuminates their combined impact on transforming breast cancer diagnosis. This integration offers insights into early identification and precise characterization of cancers. With a foundation in 125 research articles, this article presents a comprehensive overview of the current state of image-based breast cancer detection. Synthesizing the transformative role of AI, including image processing, ML, and DL, the review explores how these technologies collectively reshape the landscape of breast cancer diagnosis and severity assessment. An essential aspect highlighted is the synergy between advanced image processing methods and ML algorithms. This combination facilitates the automated examination of medical images, which is crucial for detecting minute anomalies indicative of breast cancer. The utilization of complex neural networks for feature extraction and pattern recognition in DL models further enhances diagnostic precision. Beyond diagnostic improvements, the abstract underscores the substantial influence of AI-driven methods on breast cancer treatment. The integration of AI not only increases diagnostic precision but also opens avenues for individualized treatment planning, marking a paradigm shift toward personalized medicine in breast cancer care. However, challenges persist, with issues related to data quality and interpretability requiring continued research efforts. Looking forward, the abstract envisions future directions for breast cancer identification and diagnosis, emphasizing the adoption of explainable AI techniques and global collaboration for data sharing. These initiatives promise to propel the field into a new era characterized by enhanced efficiency and precision in breast cancer care.

Identification of the best method for detecting surface water in Sentinel-2 multispectral satellite imagery

Surface water maps are useful in a variety of disciplines from climate change analysis to water resource management. Multispectral satellite imagery can be used to derive such surface water maps using a variety of image processing methods. The medium resolution Sentinel-2 multispectral satellite imagery catalogue is currently used extensively for surface water mapping. The quality and accuracy of these maps produced from Sentinel-2 imagery can vary greatly depending on the method applied to classify the image pixels into land or water. Thus far, there has not been a consensus on which method produces the highest accuracy surface water maps, warranting a direct comparison to assess these methods in a wide range of geographic settings. Here we show that among some of the most commonly applied surface water mapping methods (NDWI, MNDWI, AWEI_SH, AWEI_NSH, AWEI_BOTH, SVM, RT, MLC, and KNN) that no single method produced the most accurate maps across the four locations studied, but AWEI_NSH performed the best overall across the four locations, and SVM was the best performing machine learning technique. Rather, each method's performance was shown to depend on the objects present in the image (e.g., built-up, shadows, vegetated shorelines, narrow waterbodies, etc.) and how successfully the method was able to classify those objects properly. This is in-line with current understanding of spectral index methods' performance, and we provide recommendations to aid remote sensing data users in choosing a suitable method based on their image's characteristics. Using these recommendations, we hope that the quality of surface water maps derived from multispectral satellite imagery will be improved for all disciplines that utilize such data by allowing users to choose the method that is best fit to the application.

Towards Environmental Sustainability: Integrating RS and GIS for Ecology Assessment

The environment provides numerous benefits for human well-being, such as ecosystem services. These services directly and indirectly depend on the physical state of the ecosystem. However, the over-exploitation of natural resources along with socio-economic factors, i.e. economic growth, poverty, agriculture expansion, population growth and weak environmental governance and regulation for fulfilling the human needs for food, fuel, and shelter, is leading to the degradation of the ecological health of an area. Therefore, monitoring and assessment of spatial and temporal changes in the ecology of a region in terms of vital ecological services is very critical and would help the decision-makers to develop and plan appropriate adaptation and mitigation measures for the conservation of natural ecosystems at various scales to ensure environmental sustainability. The present study aimed to assess the ecological status of the Mahi Bajaj Sagar catchment area in Rajasthan (India) from the year 2000 to 2020, using remote sensing-based indices. Indicators such as greenness, dryness, and heat index have been selected as per the pressure-state-response (PSR) framework. Multi-spectral remote sensing data and image processing methods have been used to estimate these indicators, and a remote sensing-based Ecological Status Index (RSBI) has been generated by their integration using the principal component analysis (PCA) to assess the ecological status of the Mahi Bajaj Sagar catchment. Findings from the study indicate a consistent decline in the overall ecological status of the Mahi Bajaj catchment, where decreased forest areas have a pronounced effect on ecological health. Interestingly, approximately 43.6% of the area displayed resilience to changes in ecological status; however, 36.4% of the area exhibited signs of ecological degradation. Our study underscores the efficacy of a remote sensing-based approach in quantifying and detecting ecological changes, offering a promising methodology for monitoring and assessing the ecological health of large areas that can help promote environmental sustainability. Keywords: Environmental Sustainability, Ecological Status, RSBI, Remote Sensing, PSR Framework

Self-supervised learning-based re-parameterization instance segmentation for hazardous object in terahertz image

Recently, terahertz imaging technology has shown widespread potential applications in the public security screening field. Previous terahertz hazardous object detection techniques primarily relied on manual recognition and image processing methods. Some solutions incorporating deep learning technologies depend on large quantities of high-quality data, making it challenging to achieve low-cost and high-performance detection. To solve the issue of dependency on large amounts of high-quality data, we propose a diversified dynamic structure You Only Look Once (DDS-YOLO) model based on masked image modeling and structural reparameterization for the instance segmentation of hazardous objects in terahertz security inspection images. To address the scarcity and annotating difficulty problems of terahertz security inspection image samples, we combine automatic data strategies with masked image modeling for self-supervised learning. We propose a multilevel feature refinement fusion mechanism to enhance the quality of learned feature representations. The backbone parameter transfer and fine-tuning training strategies are employed to achieve hazardous object instance segmentation on the terahertz dataset. To address the low detection accuracy issue caused by the poor terahertz image quality, we develop a reparameterizable hierarchical structure for the backbone, improve a multi-scale feature-integrating neck, and design a dynamically decoupled head with lower computational requirements to enhance the performance of the instance segmentation model. Experimental results demonstrate that the proposed model accurately outputs detection boxes, categories, and segmentation masks for hazardous objects with minimal training samples. The comparative experimental results indicate that the proposed model outperforms existing state-of-the-art methods in terms of detection performance. The proposed DDS-YOLO model achieves 59.3 % in mask mean Average Precision (mAP) and 61.3 % in box mAP, and the model parameters and computational requirements also meet practical application scenarios.

Evaluation of asphalt anti-cracking performance of SBS polymer with SCB method and deep learning

In recent years, there have been unprecedented developments in artificial intelligence. Object detection, voice recognition, face recognition etc. are some of the artificial intelligence applications. In this study, an auxiliary method for the automatic detection of cracks, one of the main deterioration problems on highways, is proposed. The crack formation of hot mix asphalts is investigated with an image processing method modeled with Attention SegNet architecture. Styrene-butadiene-styrene (SBS), the most widely used additive in bitumen modification, was used at 2 %, 3 %, and 4 % ratios to modify 50/70 bitumen. Semi-circular asphalt specimens obtained with SBS modified bitumen were subjected to a semicircular bending (SCB) test and fracture performance was investigated. The effects of different temperature, notch size and additive on crack detection performance are evaluated. In the experimental study, maximum load, fracture energy, fracture toughness (KIC) values were obtained at low temperature, and resistance values against crack propagation were obtained by applying the J-integral method at intermediate temperature. The results demonstrated that with the addition of SBS, the fracture strength and maximum load values increased at each temperature value, with the 4 % SBS mixture offering the highest performance. Moreover, the image segmentation performed with SegNet provided high accuracy and precision values for cracks. It was observed that the accuracy values of the image processing methods decreased at low temperature, while at high temperature, higher accuracy values were obtained as the cracking rate.

Non-Destructive Identification of Virgin Cashmere and Chemically Modified Wool Fibers Based on Fractional Order Derivative and Improved Wavelength Extraction Algorithm Using NIR Spectroscopy and Chemometrics

ABSTRACT Virgin cashmere is highly prized for its superior quality, and chemically modified wool is often used to fake it. However, traditional spectral analysis and image processing methods struggle to identify the two fibers. To address this, combining chemometrics with near-infrared (NIR) spectroscopy is proposed to identify virgin cashmere and chemically modified wool based on fractional order derivatives and improved wavelength extraction algorithm. The original spectra of the two fibers are very close, making identification difficult. Therefore, fractional order derivatives are used to amplify tiny spectral differences, which are often overlooked in conventional analysis. Meanwhile, common wavelength extraction algorithms few consider inherent relationship between spectral features and chemical properties, so an improved wavelength extraction algorithm using Shuffled Frog Leaping Algorithm (SFLA) and Beluga Whale Optimization (BWO) is employed to explore the connection of the two. The proposed method with Partial Least Squares Discriminant Analysis (PLS-DA) achieves an accuracy of 94.4%. Experimental results demonstrate that fractional order derivatives enhance tiny spectral features and differences, while extracted feature wavelengths correspond to main chemical characteristic bands of the fibers. This study shows the feasibility of identifying virgin cashmere and chemically modified wool and offers a novel idea for identifying fibers in the textile industry.

Digital Protection and Inheritance Path of Intangible Cultural Heritage based on Image Processing Algorithm

This research paper introduces a novel approach in the realm of digital preservation and inheritance of Intangible Cultural Heritage (ICH) through a Customized 3D Convolutional Neural Network (CNN). The core of this study lies in the development of an advanced image processing algorithm tailored to accurately recognize, categorize, and archive diverse forms of ICH, which include traditional performances, ceremonies, oral traditions, and crafts. Utilizing a volumetric 3D CNN, this paper demonstrates how complex ICH elements can be effectively captured and analyzed, overcoming the limitations of traditional 2D image processing methods. The network is trained on a comprehensive dataset of ICH imagery, ensuring sensitivity to the subtle nuances and dynamic nature of these cultural expressions. This paper highlights the algorithm’s capability in not only safeguarding the visual aspects of ICH but also in providing an interactive, digital medium for education and cultural dissemination. The proposed method shows significant promise in aiding the efforts of cultural preservationists and educators, offering a technologically advanced pathway for the protection and inheritance of the world’s rich, yet vulnerable, cultural heritage. This study sets a precedent in the interdisciplinary field of cultural heritage conservation, digital technology, and artificial intelligence, providing a scalable and effective solution for global ICH preservation initiatives.