Gray Level Co-occurrence Matrix Texture Research Articles

Use of Sentinel-1 Dual Polarization Multi-Temporal Data with Gray Level Co-Occurrence Matrix Textural Parameters for Building Damage Assessment

Use of Sentinel-1 Dual Polarization Multi-Temporal Data with Gray Level Co-Occurrence Matrix Textural Parameters for Building Damage Assessment

Optimization of knee cartilage texture analysis of quantitative MRI T2 maps

Optimization of knee cartilage texture analysis of quantitative MRI T2 maps

Orbita hyperspectral satellite image for land cover classification using random forest classifier

The Orbita hyperspectral satellite (OHS) is the first commercial hyperspectral satellite in China that completed launching and networking. It can collect world-class hyperspectral data and obtain aerial hyperspectral imagery with 32 bands covering the spectrum range from 400 to 1000 nm at a 10-m resolution, which are of great significance for the quantitative analyses of remote sensing and refined recognitions of land covers. We explore the potentiality of the OHS image in land cover classification (LCC). Taking the Pearl River Delta region as the study area, we selected five feature indices from OHS data, i.e., original bands (OBs), vegetation indices (VIs), water indices (WIs), red edge indices (REIs), and gray-level co-occurrence matrix (GLCM) textures for the LCC. Then, data combination schemes were intended to analyze and compare the performance of different feature indices on the accuracies of the LCC. Last, feature optimization was performed on all input variables to determine the optimal variables combination to increase the accuracy and efficiency of the LCC. The random forest classifier was adopted in the above schemes, and the method of mean decrease in accuracy was used to determine the importance of the variables. The results show that (1) refined accuracy of LCC was obtained using only OBs; in addition, REIs can further improve the classification accuracy significantly. (2) The optimal variables combination achieves the highest classification accuracy (OA = 93.21 % and kappa coefficient = 0.91), and the user’s and producer’s accuracies exceeded 90% for most land cover categories. (3) Variable importance analyses show that the importance of both red-edge bands and REIs were greater than those of near-infrared bands and VIs for the LCC. The importance ranking of different indices from high to low was REIs > OBs > GLCM > WIs > VIs. This research demonstrates the potentialities and values of the OHS image for the application of LCC.

Green Infrastructure Mapping in Urban Areas Using Sentinel-1 Imagery

High temporal resolution of synthetic aperture radar (SAR) imagery (e.g., Sentinel-1 (S1) imagery) creates new possibilities for monitoring green vegetation in urban areas and generating land-cover classification (LCC) maps. This research evaluates how different pre-processing steps of SAR imagery affect classification accuracy. Machine learning (ML) methods were applied in three different study areas: random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB). Since the presence of the speckle noise in radar imagery is inevitable, different adaptive filters were examined. Using the backscattering values of the S1 imagery, the SVM classifier achieved a mean overall accuracy (OA) of 63.14%, and a Kappa coefficient (Kappa) of 0.50. Using the SVM classifier with a Lee filter with a window size of 5×5 (Lee5) for speckle reduction, mean values of 73.86% and 0.64 for OA and Kappa were achieved, respectively. An additional increase in the LCC was obtained with texture features calculated from a grey-level co-occurrence matrix (GLCM). The highest classification accuracy obtained for the extracted GLCM texture features using the SVM classifier, and Lee5 filter was 78.32% and 0.69 for the mean OA and Kappa values, respectively. This study improved LCC with an evaluation of various radiometric and texture features and confirmed the ability to apply an SVM classifier. For the supervised classification, the SVM method outperformed the RF and XGB methods, although the highest computational time was needed for the SVM, whereas XGB performed the fastest. These results suggest pre-processing steps of the SAR imagery for green infrastructure mapping in urban areas. Future research should address the use of multitemporal SAR data along with the pre-processing steps and ML algorithms described in this research.

Machine learning classification on texture analyzed T2 maps of osteoarthritic cartilage: oulu knee osteoarthritis study

To introduce local binary pattern (LBP) texture analysis to cartilage osteoarthritis (OA) research and compare the performance of different classification systems in discrimination of OA subjects from healthy controls using gray-level co-occurrence matrix (GLCM) and LBP texture data. Classification algorithms were used to reduce the dimensionality of texture data into a likelihood of subject belonging to the reference class. T2 relaxation time mapping with multi-slice multi-echo spin echo sequence was performed for eighty symptomatic OA patients and 63 asymptomatic controls on a 3T clinical MRI scanner. Relaxation time maps were subjected to GLCM and LBP texture analysis, and classification algorithms were deployed with an in-house developed software. Implemented algorithms were K nearest neighbors, support vector machine, and neural network classifier. LBP and GLCM discerned OA patients from controls with a significant difference in all studied regions. Classification models comprising GLCM and LBP showed high accuracy in classing OA patients and controls. The best performance was obtained with a multilayer perceptron type classifier with an overall accuracy of 90.2 %. LBP texture analysis complements prior results with GLCM, and together LBP and GLCM serve as significant input data for classification algorithms trained for OA assessment. Presented algorithms are adaptable to versatile OA evaluations also for future gradational or predictive approaches.

Incident Angle Dependence of Sentinel-1 Texture Features for Sea Ice Classification

Robust and reliable classification of sea ice types in synthetic aperture radar (SAR) images is needed for various operational and environmental applications. Previous studies have investigated the class-dependent decrease in SAR backscatter intensity with incident angle (IA); others have shown the potential of textural information to improve automated image classification. In this work, we investigate the inclusion of Sentinel-1 (S1) texture features into a Bayesian classifier that accounts for linear per-class variation of its features with IA. We use the S1 extra-wide swath (EW) product in ground-range detected format at medium resolution (GRDM), and we compute seven grey level co-occurrence matrix (GLCM) texture features from the HH and the HV backscatter intensity in the linear and logarithmic domain. While GLCM texture features obtained in the linear domain vary significantly with IA, the features computed from the logarithmic intensity do not depend on IA or reveal only a weak, approximately linear dependency. They can therefore be directly included in the IA-sensitive classifier that assumes a linear variation. The different number of looks in the first sub-swath (EW1) of the product causes a distinct offset in texture at the sub-swath boundary between EW1 and the second sub-swath (EW2). This offset must be considered when using texture in classification; we demonstrate a manual correction for the example of GLCM contrast. Based on the Jeffries–Matusita distance between class histograms, we perform a separability analysis for 57 different GLCM parameter settings. We select a suitable combination of features for the ice classes in our data set and classify several test images using a combination of intensity and texture features. We compare the results to a classifier using only intensity. Particular improvements are achieved for the generalized separation of ice and water, as well as the classification of young ice and multi-year ice.

Automated machine learning based plant stress detection system

Agriculture is one of the primary sources of Indian economy as majority of the population depends on agriculture. Early detection of plant stress functions an evident role in smart agriculture. In order to improve the quality and quantity of food crop and to prevent the damage caused to the plant, it is necessary to detect the stress in plant using environmental parameters. Visual sensor along with environmental sensors helps to identify the colour change in leaves of the plant at the initial stage thereby reducing the damage. An efficient plant stress detection framework is proposed which is automated for ease of use for farmers. The framework makes use of camera for capturing the images of the leaves in the field and machine learning for classifying the leaves as healthy or unhealthy. Support vector machine algorithm makes use of the features extracted from the leaves for training the system and the input features are alone transmitted to the cloud. The agricultural consultant at the other end retrieves the features and the stress is detected with the help of classification. Gray level co-occurrence matrix textures are used for extracting the features from the healthy and unhealthy leaves. Metrics such as Accuracy in classification and stress detection is validated in the proposed system.

MRI-based radiomics for prognosis of pediatric diffuse intrinsic pontine glioma: an international study.

BackgroundDiffuse intrinsic pontine gliomas (DIPGs) are lethal pediatric brain tumors. Presently, MRI is the mainstay of disease diagnosis and surveillance. We identify clinically significant computational features from MRI and create a prognostic machine learning model.MethodsWe isolated tumor volumes of T1-post-contrast (T1) and T2-weighted (T2) MRIs from 177 treatment-naïve DIPG patients from an international cohort for model training and testing. The Quantitative Image Feature Pipeline and PyRadiomics was used for feature extraction. Ten-fold cross-validation of least absolute shrinkage and selection operator Cox regression selected optimal features to predict overall survival in the training dataset and tested in the independent testing dataset. We analyzed model performance using clinical variables (age at diagnosis and sex) only, radiomics only, and radiomics plus clinical variables.ResultsAll selected features were intensity and texture-based on the wavelet-filtered images (3 T1 gray-level co-occurrence matrix (GLCM) texture features, T2 GLCM texture feature, and T2 first-order mean). This multivariable Cox model demonstrated a concordance of 0.68 (95% CI: 0.61–0.74) in the training dataset, significantly outperforming the clinical-only model (C = 0.57 [95% CI: 0.49–0.64]). Adding clinical features to radiomics slightly improved performance (C = 0.70 [95% CI: 0.64–0.77]). The combined radiomics and clinical model was validated in the independent testing dataset (C = 0.59 [95% CI: 0.51–0.67], Noether’s test P = .02).ConclusionsIn this international study, we demonstrate the use of radiomic signatures to create a machine learning model for DIPG prognostication. Standardized, quantitative approaches that objectively measure DIPG changes, including computational MRI evaluation, could offer new approaches to assessing tumor phenotype and serve a future role for optimizing clinical trial eligibility and tumor surveillance.

Machine Learning Enabled Early Detection of Breast Cancer by Structural Analysis of Mammograms

Clinical image processing plays a significant role in healthcare systems and is currently a widely used methodology. In carcinogenic diseases, time is crucial; thus, an image’s accurate analysis can help treat disease at an early stage. Ductal carcinoma in situ (DCIS) and lobular carcinoma in situ (LCIS) are common types of malignancies that affect both women and men. The number of cases of DCIS and LCIS has increased every year since 2002, while it still takes a considerable amount of time to recommend a controlling technique. Image processing is a powerful technique to analyze preprocessed images to retrieve useful information by using some remarkable processing operations. In this paper, we used a dataset from the Mammographic Image Analysis Society and MATLAB 2019b software from MathWorks to simulate and extract our results. In this proposed study, mammograms are primarily used to diagnose, more precisely, the breast’s tumor component. The detection of DCIS and LCIS on breast mammograms is done by preprocessing the images using contrast-limited adaptive histogram equalization. The resulting images’ tumor portions are then isolated by a segmentation process, such as threshold detection. Furthermore, morphological operations, such as erosion and dilation, are applied to the images, then a gray-level co-occurrence matrix texture features, Harlick texture features, and shape features are extracted from the regions of interest. For classification purposes, a support vector machine (SVM) classifier is used to categorize normal and abnormal patterns. Finally, the adaptive neuro-fuzzy inference system is deployed for the amputation of fuzziness due to overlapping features of patterns within the images, and the exact categorization of prior patterns is gained through the SVM. Early detection of DCIS and LCIS can save lives and help physicians and surgeons todiagnose and treat these diseases. Substantial results are obtained through cubic support vector machine (CSVM), respectively, showing 98.95% and 98.01% accuracies for normal and abnormal mammograms. Through ANFIS, promising results of mean square error (MSE) 0.01866, 0.18397, and 0.19640 for DCIS and LCIS differentiation during the training, testing, and checking phases.

Incidence Angle Dependence of Texture Statistics From Sentinel-1 HH-Polarization Images of Winter Arctic Sea Ice

The proliferation of synthetic aperture radar (SAR) imagery, its accessibility in open platforms like Google Earth Engine, and the development of automated classification and geophysical information extraction algorithms have prompted the need for understanding the role of incidence angle (IA) on radar scattering mechanism, backscatter intensity, and classification accuracy. This letter demonstrates the dependence of image texture parameters on SAR IA, using Arctic landfast sea ice samples extracted from C-band frequency Sentinel-1 SAR scenes collected during the winter period. Gray-level cooccurrence matrix (GLCM) derived texture parameters, and occurrence texture parameters, derived from undeformed first-year sea ice and multi-year sea ice, which are dominated by surface and volume scattering mechanisms, respectively, were analyzed. All GLCM texture parameters were found to be dependent on IA, highlighting the need for consideration of angular dependence in texture parameters, particularly in the development of image classification and inversion algorithms utilizing them. Occurrence texture parameters showed negligible influence by IA; however, feature discrimination capability was also lost. Some GLCM parameters had similar angular dependencies for both sea ice types, suggesting that, in some cases, global image normalization approaches for texture may be applied to account for the IA effect.

Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods

Spatially explicit information on tree species composition is important for both the forest management and conservation sectors. In combination with machine learning algorithms, very high-resolution satellite imagery may provide an effective solution to reduce the need for labor-intensive and time-consuming field-based surveys. In this study, we evaluated the possibility of using multispectral WorldView-3 (WV-3) satellite imagery for the classification of three main tree species (Quercus robur L., Carpinus betulus L., and Alnus glutinosa (L.) Geartn.) in a lowland, mixed deciduous forest in central Croatia. The pixel-based supervised classification was performed using two machine learning algorithms: random forest (RF) and support vector machine (SVM). Additionally, the contribution of gray level cooccurrence matrix (GLCM) texture features from WV-3 imagery in tree species classification was evaluated. Principal component analysis confirmed GLCM variance to be the most significant texture feature. Of the 373 visually interpreted reference polygons, 237 were used as training polygons and 136 were used as validation polygons. The validation results show relatively high overall accuracy (85%) for tree species classification based solely on WV-3 spectral characteristics and the RF classification approach. As expected, an improvement in classification accuracy was achieved by a combination of spectral and textural features. With the additional use of GLCM variance, the overall accuracy improved by 10% and 7% for RF and SVM classification approaches, respectively.

Prediction of Surface Roughness of Turning Operations Using Computer Vision (Dept.M)

It is well known that measuring surface roughness is vital to quality control of the machined work piece. Recently, vision systems have been applied in industries for quality control and online inspection. Thus, measuring surface roughness using computer vision became easier and more flexible. Texture features are one of the most important techniques that have been utilized in industries in many applications. In this pap er, the texture features of the gray level co-occurrence matrix (GLCM) have been utilized to predict surface roughness of specimens machined by tuning operations. The relationship between GLCM texture features and surface roughness has been investigated to discover which texture features can be used to predict surface roughness. The correlation coefficient between each texture feature and the arithinetic average height (Ra) was calculated and discussed. The investigation showed that six texture features are highly correlated with Ra. Therefore, a software has been developed to predict surface roughness for specimens machined by turning operations using these texture features. The results showed that the maximum percentage of error between the actual Ra and the predicted Ra was about ±7%.

Classification of EEG Spectrogram Image with ANN Approach for Brainwave Balancing Application

In this paper, an Artificial Neural Network (ANN) algorithm for classifying the EEG spectrogram images in brainwave is presented. Gray Level Co-occurrence Matrix (GLCM) texture feature from the EEG spectrogram images have been used as input to the system. The GLCM texture feature produced large dimension of feature, therefore the Principal Component Analysis(PCA) is used to reduce the feature dimension. The result shows that the proposed model is able to classify EEG spectrogram images with 77% to 84% accuracy for three classes of brainwave balancing application with an optimized ANN model in training by varying the neurons in the hidden layer, epoch, momentum rate and learning rate.

Feature Extraction for Cocoa Bean Digital Image Classification Prediction for Smart Farming Application

The implementation of Industry 4.0 emphasizes the capability and competitiveness in agriculture application, which is the essential framework of a country’s economy that procures raw materials and resources. Human workers currently employ the traditional assessment method and classification of cocoa beans, which requires a significant amount of time. Advanced agricultural development and procedural operations differ significantly from those of several decades earlier, principally because of technological developments, including sensors, devices, appliances, and information technology. Artificial intelligence, as one of the foremost techniques that revitalized the implementation of Industry 4.0, has extraordinary potential and prospective applications. This study demonstrated a methodology for textural feature analysis on digital images of cocoa beans. The co-occurrence matrix features of the gray level co-occurrence matrix (GLCM) were compared with the convolutional neural network (CNN) method for the feature extraction method. In addition, we applied several classifiers for conclusive assessment and classification to obtain an accuracy performance analysis. Our results showed that using the GLCM texture feature extraction can contribute more reliable results than using CNN feature extraction from the final classification. Our method was implemented through on-site preprocessing within a low-performance computational device. It also helped to foster the use of modern Internet of Things (IoT) technologies among farmers and to increase the security of the food supply chain as a whole.

A Quantitative Monitoring Method for Determining Maize Lodging in Different Growth Stages

Many studies have achieved efficient and accurate methods for identifying crop lodging under homogeneous field surroundings. However, under complex field conditions, such as diverse fertilization methods, different crop growth stages, and various sowing periods, the accuracy of lodging identification must be improved. Therefore, a maize plot featuring different growth stages was selected in this study to explore an applicable and accurate lodging extraction method. Based on the Akaike information criterion (AIC), we propose an effective and rapid feature screening method (AIC method) and compare its performance using indexed methods (i.e., variation coefficient and relative difference). Seven feature sets extracted from unmanned aerial vehicle (UAV) images of lodging and nonlodging maize were established using a canopy height model (CHM) and the multispectral imagery acquired from the UAV. In addition to accuracy parameters (i.e., Kappa coefficient and overall accuracy), the difference index (DI) was applied to search for the optimal window size of texture features. After screening all feature sets by applying the AIC method, binary logistic regression classification (BLRC), maximum likelihood classification (MLC), and random forest classification (RFC) were utilized to discriminate among lodging and nonlodging maize based on the selected features. The results revealed that the optimal window sizes of the gray-level cooccurrence matrix (GLCM) and the gray-level difference histogram statistical (GLDM) texture information were 17 × 17 and 21 × 21, respectively. The AIC method incorporating GLCM texture yielded satisfactory results, obtaining an average accuracy of 82.84% and an average Kappa value of 0.66 and outperforming the index screening method (59.64%, 0.19). Furthermore, the canopy structure feature (CSF) was more beneficial than other features for identifying maize lodging areas at the plot scale. Based on the AIC method, we achieved a positive maize lodging recognition result using the CSFs and BLRC. This study provides a highly robust and novel method for monitoring maize lodging in complicated plot environments.

TEXTURE ANALYSIS FOR LAND USE LAND COVER (LULC) CLASSIFICATION IN PARTS OF AHMEDABAD, GUJARAT

Abstract. The present study addresses the potential of RADARSAT-2 data for Land Use Land Cover (LULC) Classification in parts of Ahmedabad, Gujarat, India. Texture measures of the original SAR data were obtained by the Gray Level Co-occurrence Matrix (GLCM). Results suggested False Colour Composite (FCC) of Mean, Homogeneity and Entropy showed a good discrimination of different land cover classes. Further, Principal Component Analysis (PCA) was also applied to the eight texture measures and FCC of Principal components is generated. Unsupervised classification is carried out for the above generated FCCs and accuracy assessment is carried out. The result of classification shows that the PCA generated from GLCM texture measures could obtain higher accuracy than using only the classification carried out by texture measures. Overall results of the study suggested possible use of single polarization and single date Radarsat-2 data for LULC classification with better accuracy using PCA generated image.

Classification of sea ice types in Sentinel-1 synthetic aperture radar images

Abstract. A new Sentinel-1 image-based sea ice classification algorithm using a machine-learning-based model trained in a semi-automated manner is proposed to support daily ice charting. Previous studies mostly rely on manual work in selecting training and validation data. We show that the readily available ice charts from the operational ice services can reduce the amount of manual work in preparation of large amounts of training/testing data. Furthermore, they can feed highly reliable data to the trainer by indirectly exploiting the best ability of the sea ice experts working at the operational ice services. The proposed scheme has two phases: training and operational. Both phases start from the removal of thermal, scalloping, and textural noise from Sentinel-1 data and calculation of grey level co-occurrence matrix and Haralick texture features in a sliding window. In the training phase, the weekly ice charts are reprojected into the SAR image geometry. A random forest classifier is trained with the texture features on input and labels from the rasterized ice charts on output. Then, the trained classifier is directly applied to the texture features from Sentinel-1 images operationally. Test results from the two datasets spanning winter (January–March) and summer (June–August) seasons acquired over the Fram Strait and the Barents Sea showed that the classifier is capable of retrieving three generalized cover types (open water, mixed first-year ice, old ice) with overall accuracies of 87 % and 67 % in winter and summer seasons, respectively. For the summer season, the classifier failed in distinguishing mixed first-year ice from old ice with accuracy of only 12 %; however, it performed rather like an ice–water discriminator with high accuracy of 98 % as the misclassification between the mixed first-year ice and old ice was between them. The accuracy for five cover types (open water, new ice, young ice, first-year ice, old ice) in the winter season was 60 %. The errors are attributed both to incorrect manual classification on the ice charts and to the semi-automated algorithm. Finally, we demonstrate the potential for near-real-time service of the ice map using daily mosaicked Sentinel-1 images.

Detecting Lesion Characteristics of Diabetic Retinopathy Using Machine Learning and Computer Vision

One indicator of the severity of diabetic retinopathy is the existence of lesion characteristics in the eyes such as microaneurysm, hemorrhages, exudates, and neovascularization. Without proper early medical attention, this lesion could lead to blindness. Considering its importance, a system that could detect such lesions will be beneficial. This paper investigates the lesion characteristics of diabetic retinopathy from fundus images such as microaneurysm (redsmalldots), exudates, hemorrhages, and neovascularization. In this study, we present three of feature extraction methods, i.e., Local Binary Pattern (LBP), Gray Level Co-Occurrence Matrix (GLCM) and Segmentation Fractal Texture Analysis (SFTA). K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) chosen as classifiers for classifying five classes (redsmalldots, hemorrhages, hard exudates, soft exudates, and neovascularization). The data used in this research obtained from DiaretDB0 database. The experimental results show that our proposed method can detect the lesion characteristics of diabetic retinopathy with higher accuracy of 86,84% and 96% for SVM and KNN, respectively.

Adopting multispectral dip components for coherence and curvature attribute computations

Although volumetric coherence is the most widely used geometric attribute, accurate estimates of volumetric dip are in some ways more important. Coherence, amplitude gradients, and gray-level co-occurrence matrix textures should be computed along structural dip. Curvature and aberrancy are computed from volumetric estimates of structural dip. Because of both differences in resolution and sensitivity to coherent noise, different frequency components may exhibit different dip. In recent years, improvements in coherence have been noticed where covariance matrices of individual spectral components are summed rather than summing the original broadband data. We extend the same concepts to compute multispectral dip estimates by using a gradient structure tensor algorithm. The results are sharper, less smeared images on the dip components. The higher-resolution dip estimates result in higher-resolution curvature and aberrancy estimates. Availability of sharper estimates of dip to guide coherence attribute results in more continuous, less noisy discontinuities.

Extraction of Sea Ice Cover by Sentinel-1 SAR Based on Support Vector Machine With Unsupervised Generation of Training Data

In this article, we focus on developing a novel method to extract sea ice cover (i.e., discrimination/classification of sea ice and open water) using Sentinel-1 (S1) cross-polarization [vertical-horizontal (VH) or horizontal-vertical (HV)] data in extra-wide (EW) swath mode based on the support vector machine (SVM) method. The classification basis includes the S1 radar backscatter and texture features, which are calculated from S1 data using the gray level co-occurrence matrix (GLCM). Different from previous methods where appropriate samples are manually selected to train the SVM to classify sea ice and open water, we proposed a method of unsupervised generation of the training samples based on two GLCM texture features, i.e., entropy and homogeneity, that have contrasting characteristics on sea ice and open water. We eliminate the most uncertainty of selecting training samples in machine learning and achieve automatic classification of sea ice and open water by using S1 EW data. The comparisons based on a few cases show good agreements between the synthetic aperture radar (SAR)-derived sea ice cover using the proposed method and visual inspections, of which the accuracy reaches approximately 90%-95%. Besides this, compared with the analyzed sea ice cover data Ice Mapping System (IMS) based on 728 S1 EW images, the accuracy of the extracted sea ice cover by using S1 data is more than 80%.