A novel objective wrinkle evaluation method for printed fabrics based on multi-view stereo algorithm

This paper presents a digital imaging method based on silhouette image analysis to visualize the three-dimensional (3D) surface profile of textiles, or other flexible materials, and investigates its 3D reconstruction principle. A prototype of an imaging system consisting of five components has been developed: visible lighting source (white backlighting), sample stage, progressive sample feeding equipment, detector (CCD camera), and analysis software. A sequence of silhouette images of textile surface patches was digitized progressively where a sample was passed through the sharp edge of a crossbeam in bending status, so that the whole 3D surface profile could be generated by a combination of the silhouette height profile of each surface patch in the sequence. This non-destructive testing method is effective for the surface characterization or defects detection of flexible materials. It can reconstruct a pure 3D surface profile of the surface while discarding unwanted information such as surface color. This avoids the fusion of shadows and dark colors, which is a problem when using traditional two-dimensional (2D) image analysis methods. The Kawabata Evaluation System (KES) is used to validate the effectiveness of this silhouette imaging system (SIS), and our experiment shows that good correlation can be achieved in terms of thickness and surface roughness measurements. However, there are some differences due to the contact or non-contact methods used in terms of the measurement of fuzzy layers in textile materials.

The apple surface texture feature is one of the important indicators of its quality grading. We took Fuji apples as the object of our study and obtained feature information, including the color distribution and textural properties by using computer vision technique, and then, we conducted surface texture detection through back-propagation (BP) neural network. We calculated the RGB means of collected images in RGB color model, and took the R/G mean ratio as the feature parameters of color distribution; meanwhile, we converted the collected images into gray level images and by using gray level co-occurrence matrix, we extracted the angular second moment, contrast, correlation, and entropy of apple surface texture as the texture feature parameters. We planned to detect the apple surface texture with BP neural network; took the obtained two kinds of features as the input unit of BP neural network classifier and applied one unit for output layer to output the detection result of apple surface. The test result showed that the recognition rate of the proposed method was 91.25 %, which has laid foundation for further realization of apple quality grading in accordance with surface texture.

In this paper the wrinkle property of fabrics was studied by using the projected profile light line technique. In analyzing the results, three parameters of mean deviation and the absolute of the mean values of heights extracted from the projected surface profile line on the surface of the fabric and surface area ratio were defined and studied to evaluate and characterize the fabric wrinkle. In this study 30 fabrics of different materials, colors, and patterns along different angles between warp direction and X-direction were studied. The results show that the surface characteristics of fabrics such as color or pattern have no effect on the results. According to the results, the mean deviation of height values of the projected profile light line on the surface of the fabric is a good factor in comparison with the other two evaluation factors of fabric wrinkle. This study showed that there is a strong logarithmic correlation between the mean deviation of height values of surface profiles and the subjective evaluation of wrinkle grades of the samples. In this method, there is a good agreement between the subjective appraisal and the objective evaluation of fabrics.

BackgroundThe global morbidity and mortality of prostate cancer (PCa) increase sharply every year. Early diagnosis is essential; it determines survival and outcome. So, this study extracted the texture features of apparent diffusion coefficient images in multiparametric magnetic resonance imaging (mp-MRI) and built machine learning models based on radiomics texture analysis (TA) to determine its ability to distinguish benign from PCa lesions using the Prostate Imaging Reporting and Data System (PI-RADS) 4/5 score.MethodsWe enrolled 103 patients who underwent mp-MRI examinations and transrectal ultrasound and magnetic resonance fusion imaging (TRUS-MRI) targeted prostate biopsy and obtained pathological confirmation at our hospital from August 2017 to January 2020. We used ImageJ software to obtain texture feature parameters based on apparent diffusion coefficient (ADC) images, then standardized texture feature parameters, and used LASSO regression to reduce multiple feature parameters; 70% of the cases were randomly selected from the PCa group and the benign prostate hyperplasia group as the training set. The remaining 30% was used as the test set. The machine learning classification model for identifying benign and malignant prostate lesions was constructed using the feature parameters after dimensionality reduction. The clinical indicators were statistically analyzed, and we constructed a machine learning classification model based on clinical indicators of benign and malignant prostate lesions. Finally, we compared the model’s performance based on radiomics texture features and clinical indicators to identify benign and malignant prostate lesions in PI-RADS 4/5 score.ResultsThe area under the curve (AUC) of the R-logistic model test set was 0.838, higher than the R-SVM and R-AdaBoost classification models. At this time, the corresponding R-logistic classification model formula is as follow: Y_radiomics=9.396-7.464*median ADC-0.584*kurtosis+0.627*skewness+0.576*MRI lesions volume; analysis of clinical indicators shows that the corresponding C-logistic classification model formula is as follows: Y_clinical =-2.608+0.324*PSA-3.045*Fib+4.147*LDL-C, the AUC value of the model training set was 0.860, smaller than the training set R-logistic classification model AUC value of 0.936.ConclusionsRadiomics combined with the machine learning classifier model has strong classification performance in identifying benign and PCa in PI-RADS 4/5 score. Various treatments and outcomes for PCa patients can be applied clinically.

3D reconstruction from monocular endoscopic images is a challenging task. State-of-the-art multi-view stereo (MVS) algorithms based on image patch similarity often fail to obtain a dense reconstruction from weakly-textured endoscopic images. In this paper, we present a novel deep-learning-based MVS algorithm that can produce a dense and accurate 3D reconstruction from a monocular endoscopic image sequence. Our method consists of three key steps. Firstly, a number of depth candidates are sampled around the depth prediction made by a pre-trained CNN. Secondly, each candidate is projected to the other images in the sequence, and the matching score is measured using a patch embedding network that maps each image patch into a compact embedding. Finally, the candidate with the highest score is selected for each pixel. Experiments on colonoscopy videos demonstrate that our patch embedding network outperforms zero-normalized cross-correlation and a state-of-the-art stereo matching network in terms of matching accuracy and that our MVS algorithm produces several degrees of magnitude denser reconstruction than the competing methods when same accuracy filtering is applied.

The research and development of an intelligent magnetic levitation transportation system has become an important research branch of the current intelligent transportation system (ITS), which can provide technical support for state-of-the-art fields such as intelligent magnetic levitation digital twin. First, we applied unmanned aerial vehicle oblique photography technology to acquire the magnetic levitation track image data and preprocessed them. Then, we extracted the image features and matched them based on the incremental structure from motion (SFM) algorithm, recovered the camera pose parameters of the image data and the 3D scene structure information of key points, and optimized the bundle adjustment to output 3D magnetic levitation sparse point clouds. Then, we applied multiview stereo (MVS) vision technology to estimate the depth map and normal map information. Finally, we extracted the output of the dense point clouds that can precisely express the physical structure of the magnetic levitation track, such as turnout, turning, linear structures, etc. By comparing the dense point clouds model with the traditional building information model, experiments verified that the magnetic levitation image 3D reconstruction system based on the incremental SFM and MVS algorithm has strong robustness and accuracy and can express a variety of physical structures of magnetic levitation track with high accuracy.

Remote sensing technologies provide effective means for monitoring and analyzing the environmental impacts of natural hazards. Among Earth observation approaches, optical remote sensing has remained a fundamental data source for decades. In recent years, unmanned aerial vehicles (UAVs), also referred to as drones, have emerged as a flexible and cost-effective platform for acquiring high-resolution geospatial data, including optical imagery, thermal data, and LiDAR point clouds. Owing to their high operational flexibility, UAVs are particularly suitable for collecting first-hand spatial data shortly after disaster events, supporting rapid damage assessment. This study employs UAV-based optical imagery acquired after the Noto earthquake, which occurred on 1 January 2024 in Japan, to support post-disaster geovisualization and spatial analysis. Structure-from-motion (SfM) and multi-view stereo (MVS) techniques are applied to reconstruct three-dimensional (3D) geoinformation from the UAV images. Two key products—a textured triangulated irregular network (TIN) model and an orthophoto—are generated to visualize affected areas and support geospatial analysis. The study focuses on interpreting earthquake-induced damage by integrating 3D models and texture information, with particular emphasis on road damage assessment. Texture features are extracted from orthophotos and represented using indicators derived from the grey-level co-occurrence matrix (GLCM). These texture descriptors, combined with geospatial attributes, are used as inputs to an extreme gradient boosting (XGBoost) model for semi-automatic road damage prediction. The predicted damage results are subsequently correlated with the 3D TIN models to identify locations where road damage is likely to occur. By integrating texture-based analysis with 3D geovisualization, this workflow improves the interpretation of earthquake-related damage across virtual and real-world contexts. The results indicate that UAV-derived optical imagery, combined with machine learning and 3D reconstruction techniques, can support efficient post-disaster damage assessment. This approach enables advanced simulation of decision-making processes and rescue operations, reducing unnecessary costs while improving the effectiveness and timeliness of hazard response.

This study focuses on the feature extraction and classification of surface discharges of ice-covered insulator strings during process of alternating current flashover. The test specimen was the five units suspension ceramic insulators, which was artificially accreted with wet-grown ice in the cold-climate room of CIGELE. Based on the IEEE Standard 1783/2009, flashover experiments were conducted on iced insulators to measure the minimum flashover voltage (VMF) and record the propagating process of surface discharges to flashover by using a high-speed video camera. The gray-level co-occurrence matrix (GLCM) method has been used to extract four parameters of arc discharge images features that characterize different stages of flashover process. The parameters are angular second moment (ASM), contrast (CON), inverse difference moment (IDM) and entropy (ENT). These statistical parameters of GLCM can be extracted to reveal the underlying properties of ice flashover on the insulator surface from the quantitative perspective. The different values of these indicators are representative of the different stages in the process of arc discharge. Once the value of quantitative indicators (ASM, CON, IDM, ENT) of surface discharges exceeds the threshold value, the higher flashover risk of iced insulators will appear. Hence, the proposed methods are helpful to understand and monitor surface discharge on iced outdoor insulator strings for preventing flashover accidents.

Texture and its analysis methods are crucial for image feature extraction and classification. Digital elevation model (DEM) is the most important data source of digital terrain analysis and landform classification, and considerable research values are gained from texture feature extraction and analysis from DEM data. In this research, on the basis of optimal texture feature extraction, the hilly area in Shandong, China, was selected as the study area, and DEM data with a resolution of 500 m were used as the experimental data for landform classification. First, second-order texture measures and texture image were extracted from DEM data by using a gray level cooccurrence matrix (GLCM). Second, the variation characteristics of each texture measure were analyzed, and the optimal feature parameters, such as direction, gray level, and texture window, were determined. Meanwhile, the texture feature value, combined with maximum information, was calculated, and the multiband texture image was obtained by resolving three optimal texture measure images. Finally, a support vector machine (SVM) method was adopted to classify landforms on the basis of the multiband texture image. Results indicated that the texture features of DEM data can be sufficiently represented and measured via the quantitative GLCM method. However, the feature parameters during the texture feature value calculation required further optimization. Based on the image texture from DEM data, efficient classification accuracy and ideal classification effect were achieved.

The foundation of information extraction based on remote sensing imaging involves spectral band information. Such a method often suffers from the distinctive problem of surface features. In general, artificial orchard planting is relatively regular; thus, it shows textural features that differ from other vegetation types in images with a specific spatial scale. This study used mango groves as research object. By introducing spectral index, texture feature parameters, and by using support vector machine classification method, based on GF-2 satellite images, mango grove information extraction was studied under different combinations of spectra band, vegetation index, and texture feature parameters. The findings show that the information extraction via single spectra band information has lower accuracy. Introduction of a combination of spectra index and spectra band information can improve extraction accuracy of mango groves; however, the overall classification accuracy still remains low. In addition, the introduction of texture information and spectra band information combination can dramatically improve extraction accuracy. Producer's accuracy and user's accuracy increased to 85.7% and 93.5%, respectively. Under different combination modes, the extracted mango grove accuracy of the combination of integrated spectra band information, textural feature, and vegetation index is optimal. Producer's accuracy and user's accuracy increased to 89.3% and 97.4%, respectively. Relative to the spectra band information, the extraction accuracy improved by 20.6% and 11.0%, respectively. As a result, the support vector machine of integrated spectra and texture can effectively extract the spatial distribution information of mango groves. This method can provide a technical reference for remote sensing extraction of artificial orchards.

Objective To evaluate the clinical value of magnetic resonance imaging T2WI texture analysis in the diagnosis of prostate cancer. Methods A total of 78 patients with pathological-confirmed prostate cancer and prostatic hyperplasia from Jan. 2016 to Dec. 2018 in our hospital were retrospectively collected. MaZda software was used to analyze 300 texture feature parameters of each lesion on T2WI images, and Weka software was used to select the most discriminative texture feature parameters. The differences of texture features between the two groups and diagnostic efficacy were compared by independent sample t test, Mann-Whitney U test and ROC. Results There were 7 texture feature parameters of the most discriminative significance between the two groups: AngScMom, Contrast, Entropy, Horzl_GLevNonU, 45dgr_RLNonUni, WavEnLL_s-1 and WavEnHL_s-3, respectively. There were significant differences in 7 texture feature parameters between prostate cancer group and prostate hyperplasia group (P<0.05) . The AUC of each texture feature was between 0.78 and 0.91, the accuracy was between 79.6% and 92.1%, the sensitivity was between 70.8% and 91.9%, and the specificity was between 72.2% and 92.5%, respectively. Conclusions The texture features parameters of T2WI images are different in the diagnosis of prostate cancer and prostatic hyperplasia. As an objective and quantitative analysis method, texture features analysis can be used in the differential diagnosis of prostate cancer and prostatic hyperplasia. Key words: Magnetic resonance imaging; Texture analysis; Prostate cancer; Prostatic hyperplasia

ObjectiveThe aim of this study was to assess the predictive capabilities of a radiomics signature obtained from arterial spin labeling (ASL) imaging in forecasting and detecting stages of kidney damage in patients with diabetes mellitus (DM), as well as to analyze the correlation between texture feature parameters and biological clinical indicators. Additionally, this study seeks to identify the imaging risk factors associated with early renal injury in diabetic patients, with the ultimate goal of offering novel insights for predicting and diagnosing early renal injury and its progression in patients with DM.Materials and methodsIn total, 42 healthy volunteers (Group A); 68 individuals with diabetes (Group B) who exhibited microalbuminuria, defined by a urinary albumin-to-creatinine ratio (ACR)< 30 mg/g and an estimated glomerular filtration rate (eGFR) within the range of 60–120 mL/min/1.73m²; and 53 patients with diabetic nephropathy (Group C) were included in the study. ASL using magnetic resonance imaging (MRI) at 3.0T was conducted. The radiologist manually delineated regions of interest (ROIs) on the ASL maps of both the right and left kidney cortex. Texture features from the ROIs were extracted utilizing MaZda software. Feature selection was performed utilizing a range of methods, such as the Fisher coefficient, mutual information (MI), probability of classification error, and average correlation coefficient (POE + ACC). A radiomics model was developed to detect early diabetic renal injury, extract imaging risk factors associated with early diabetic renal injury, and examine the relationship between significant texture feature parameters and biological clinical indicators. Patients with DM and kidney injury were followed prospectively. The study utilized seven machine learning algorithms to develop a detective radiomics model and a comprehensive predictive model for assessing the progression of kidney damage in patients with DM. The diagnostic efficacy of the models in detecting variations in diabetic kidney damage over time was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. Empower (R) was used to establish a correlation between clinical biological indicators and texture feature metrics. Statistical analysis was conducted using R, Python, MedCalc 15.8, and GraphPad Prism 8.ResultsA total of 367 texture features were extracted from the ROIs in the kidneys and refined based on selection criteria using MaZda software across groups A, B, and C. The renal blood flow (RBF) values of the renal cortex in groups A, B, and C exhibited a decreasing trend, with values of 256.458 ± 54.256 mL/100g/min, 213.846 ± 52.109 mL/100g/min, and 170.204 ± 34.992 mL/100g/min, respectively. There was a positive correlation between kidney RBF and eGFR (r = 0.439, P<0.001). The negative correlation between RBF and various clinical parameters including urinary albumin-to-creatinine ratio (UACR), body mass index (BMI), diastolic blood pressure (DBP), blood urea nitrogen (BUN), and serum creatinine (SCr) was investigated. Through the use of a least absolute shrinkage and selection operator (LASSO) regression model, the study identified the eight most significant texture features and biological indicators, namely GeoY, GeoRf, GeoRff, GeoRh, GeoW8, GeoW12, S (0, 4) Entropy, and S (5, -5) Entropy. Spearman correlation analysis revealed associations between imaging markers in early diabetic patients with kidney damage and factors such as age, systolic blood pressure (SBP), Alanine Transaminase (ALT), Aspartate Amino Transferase (AST) albumin, uric acid (UA), microalbuminuria (UMA), UACR, 24h urinary protein, fasting blood glucose (FBG), two hours postprandial blood glucose (P2BG), and HbA1c. The study utilized ASL imaging as a detection model to identify renal injury in patients with DM across different stages, achieving a sensitivity of 85.1%, specificity of 65.5%, and an AUC of 0.865. Additionally, a comprehensive prediction model combining imaging labels and biological indicators, with the naive Bayes machine learning algorithm as the best model, demonstrated an AUC of 0.734, accuracy of 0.74, and precision of 0.43.ConclusionASL imaging sequences demonstrated the ability to accurately detect alterations in kidney function and blood flow in patients with DM. Strong associations were observed between renal blood flow values in ASL imaging and established clinical biomarkers. These values show promise in detecting early microstructural changes in the kidneys of diabetic patients. Utilizing image markers in conjunction with clinical indicators was effective in identifying early renal dysfunction and its progression in individuals with DM. Furthermore, the integration of imaging texture feature parameters with clinical biomarkers holds significant potential for predicting early renal damage and its progression in patients with diabetes.

This paper presents a 3D face reconstruction method based on multi-view stereo algorithm, the proposed algorithm reconstructs 3D face model from videos captured around static human faces. Image sequence is processed as the input of shape from motion algorithm to estimate camera parameters and camera positions, 3D points with different denseness degree could be acquired by using a method named patch based multi-view stereopsis, finally, the proposed method uses a surface reconstruction algorithm to generate a watertight 3D face model. The proposed approach can automatically detect facial feature points; it does not need any initialization and special equipments; videos can be obtained with commonly used picture pick-up device such as mobile phones. Several groups of experiments have been conducted to validate the availability of the proposed method.

Structure-from-motion (SfM) and multi-view stereo (MVS) algorithms coupled with the use of unmanned aerial vehicles (UAVs) have become a popular tool in the geosciences for modelling complex landscapes on-demand allowing for high-resolution topographic change-detection studies to be conducted at minimal cost. To identify the effects of UAV image orientation on the accuracy of SfM-MVS 3D surface models, we tested four different UAV image acquisition schemes that incorporated both nadir and oblique imagery of an agricultural field. The coupling of nadir and oblique imaging angles led to the highest surface model accuracy in the absence of ground control points (GCPs; vertical RMSE: 0.047 m, horizontal RMSE: 0.019 m), while with a normative distribution of GCPs the nadir-only image sets had similar accuracy metrics (vertical RMSE 0.028 m, horizontal RMSE 0.017 m) to surface models generated with nadir and oblique imaging angles (vertical RMSE 0.028 m, horizontal RMSE 0.013 m). Homologous keypoint matching between nadir and oblique imagery was poor when the survey conditions were bright and the surface texture of the field was homogeneous, leading to broad-scale vertical noise in the generated surface models. Results indicate that a nadir-only image set accompanied with a dense deployment of GCPs is the most ideal for SfM-MVS agricultural 3D surface reconstructions. The diachronic analysis of surface models generated from nadir-only image sets were able to detect surface-change >0.040 m in depth (i.e., rill and gully erosion, depositional zones) and were comparable to results obtained from a terrestrial laser scanner. Stable GCPs should be used where possible to ensure precise co-registration between subsequent UAV surveys.

Structure from motion (SfM) and MultiView Stereo (MVS) algorithms are increasingly being applied to imagery from unmanned aircraft systems (UAS) to generate point cloud data for various surveying and mapping applications. To date, the options for assessing the spatial accuracy of the SfM-MVS point clouds have primarily been limited to empirical accuracy assessments, which involve comparisons against reference data sets, which are both independent and of higher accuracy than the data they are being used to test. The acquisition of these reference data sets can be expensive, time consuming, and logistically challenging. Furthermore, these experiments are also almost always unable to be perfectly replicated and can contain numerous confounding variables, such as sun angle, cloud cover, wind, movement of objects in the scene, and camera thermal noise, to name a few. The combination of these factors leads to a situation in which robust, repeatable experiments are cost prohibitive, and the experiment results are frequently site-specific and condition-specific. Here, we present a workflow to render computer generated imagery using a virtual environment which can mimic the independent variables that would be experienced in a real-world UAS imagery acquisition scenario. The resultant modular workflow utilizes Blender, an open source computer graphics software, for the generation of photogrammetrically-accurate imagery suitable for SfM processing, with explicit control of camera interior orientation, exterior orientation, texture of objects in the scene, placement of objects in the scene, and ground control point (GCP) accuracy. The challenges and steps required to validate the photogrammetric accuracy of computer generated imagery are discussed, and an example experiment assessing accuracy of an SfM derived point cloud from imagery rendered using a computer graphics workflow is presented. The proposed workflow shows promise as a useful tool for sensitivity analysis and SfM-MVS experimentation.