Co-occurrence Matrix Algorithm Research Articles

Grade Classification of Camellia Seed Oil Based on Hyperspectral Imaging Technology.

To achieve the rapid grade classification of camellia seed oil, hyperspectral imaging technology was used to acquire hyperspectral images of three distinct grades of camellia seed oil. The spectral and image information collected by the hyperspectral imaging technology was preprocessed by different methods. The characteristic wavelength selection in this study included the continuous projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS), and the gray-level co-occurrence matrix (GLCM) algorithm was used to extract the texture features of camellia seed oil at the characteristic wavelength. Combined with genetic algorithm (GA) and support vector machine algorithm (SVM), different grade classification models for camellia seed oil were developed using full wavelengths (GA-SVM), characteristic wavelengths (CARS-GA-SVM), and fusing spectral and image features (CARS-GLCM-GA-SVM). The results show that the CARS-GLCM-GA-SVM model, which combined spectral and image information, had the best classification effect, and the accuracy of the calibration set and prediction set of the CARS-GLCM-GA-SVM model were 98.30% and 96.61%, respectively. Compared with the CARS-GA-SVM model, the accuracy of the calibration set and prediction set were improved by 10.75% and 12.04%, respectively. Compared with the GA-SVM model, the accuracy of the calibration set and prediction set were improved by 18.28% and 18.15%, respectively. The research showed that hyperspectral imaging technology can rapidly classify camellia seed oil grades.

Rapid and nondestructive identification of rice storage year using hyperspectral technology

Rice is the main staple food for more than half of the world's population. Consumption of long-stored rice will have adverse effects on the human body. Here, we proposed the near-infrared (NIR) hyperspectral imaging (HSI) technique to distinguish rice from different storage years. Multiplicative Scatter Correction (MSC), Standard Normalize Variate (SNV) and 1st Derivative (1st) were used for the pretreatment of HSI data. In order to reduce dimensional spectral features, Principal Component Analysis (PCA) and t-distributed Stochastic Neighbor Embedding (tSNE) were used for data visualization. Besides, spectral characteristic wavelengths were extracted by competitive adaptive reweighted sampling (CARS) and least absolute shrinkage and selection operator (Lasso). Simultaneously, the textural features of rice were analyzed by Local Binary Pattern (LBP), Gray-Level Co-occurrence Matrix (GLCM) and Tamura algorithms. In order to realize feature fusion of spectra and texture, Support Vector Machine (SVM) model was optimized using the Whale optimization algorithm (WOA) and Extreme Gradient Boosting (XGBoost) model were established based on spectral features and textural features. Compared to other models, feature fusion model showed an excellent result with an accuracy of 98.89%. Experimental results suggested that HSI technology can be served as an effective method for rice detection.

Classification and identification of pest, diseases and nutrient deficiency in paddy using layer based EMD phase features with decision tree

Pest attack, disease incidence, and nutrient deficiency are the major factors limiting the yield of paddy. Therefore, the paper proposes a classification system for the identification of pest, disease, and nutrient deficiency classes. This approach initially preprocesses leaf images using entropy filtering followed by a leaf segmentation process. Multiple layers are then constructed on the leaf image through which features are extracted. The Gray Level Co-occurrence Matrix (GLCM) algorithm and Principal Component Analysis (PCA) are used to extract the global texture features of the leaf image. A 1D-signal sequence is constructed on each layer, which is decomposed by the Empirical Mode Decomposition algorithm from which the phase features are estimated. The features are trained/classified using the decision tree classifiers that classify the pest attack, disease incidence, and nutrient deficiency categories. The proposed approach provides a precision, accuracy, specificity, sensitivity, and F1-score of 97 %, 97.88 %, 96.52 %, 96.7 %, and 96.7 % respectively.

Image Analysis and Classification Using HRSVM-CNN for Land-Cover Classification by Using Remote Sensing Images

Objective: To effectively analyze diverse satellite images and derive valuable insights, it's crucial to employ efficient methods for classification and image processing. However, due to imperfections in image formats and sensor data, satellite imagery often contains flaws and inaccuracies, requiring extra steps to enhance its quality. The proposed solution involves two key techniques: segmenting the input image using a Hybrid HRSVM-CNN and classifying the resulting high-resolution remote sensing image using a Convolutional Neural Network. This combined approach addresses the challenges posed by image inconsistencies and aims to improve the accuracy and efficiency of current methods for satellite image analysis. Methods: In this research, a high-resolution Support Vector Machine-Convolutional Neural Network (Hybrid HRSVM-CNN) and texture characteristics are used to create an automated land identification method for satellite Remote sensing (RS) images. This approach's main focus is segmentation using the Bendlet Transform and Improved Chan-Vese, and it also does classification using a Hybrid HRSVM-CNN based on feature extraction and gray-level co-occurrence matrix algorithm. Findings: The proposed classification method's accuracy was evaluated against several other classification algorithms, including Semi-Supervised Graph Based Method (SSG), Conditional Random Fields (CRF), k-Nearest Neighbor (KNN), and Bi-layer Graph-based Learning (BLGL), Support Vector Machine (SVM), and Artificial Neural Networks (ANN). When compared with existing methods, the findings of the proposed method display excellent accuracy of 98.83%. Novelty: To start, an adaptive median filter is used to pre-process the satellite Remote sensing images, removing unwanted noises and other impacts. Following pre-processing, the image is segmented using the Bendlet Transform and Improved Chan-Vese algorithms. Gray-level co-occurrence matrix is utilized to extract texture information, and the Hybrid HRSVM-CNN is then used to categorize the various types of land. These applications frequently have a variety of issues that affect the categorization accuracy. A few significant factors, like location, irregularity, form, and diameter, reduce the process's overall accuracy. This research focuses on presenting a unique Land-Cover classification model in order to address such problems. The UC Merced Land Use dataset was considered in this research. Keywords: Bendlet Transform and Improved Chan­Vese Segmentation, Hybrid HRSVM­CNN, Land detection system, Satellite remote sensing images, Adaptive median filter, Gray­ level co­occurrence matrix

Process modeling and optimization in laser drilling of bulk metallic glasses based on GABPNN and machine vision

It is a challenging to ensure the quality of microholes during the laser drilling of bulk metallic glasses (BMGs), where the defects such as heat-affected zones, burrs, and low smoothness are usually obtained. Based on machine vision, back-propagation neural network (BPNN), and genetic algorithm (GA) in artificial intelligence technology, a relationship model between the microhole features and laser processing parameters was proposed, so as to predict and optimize the processing parameters during the laser drilling of BMGs. Firstly, the geometric parameters and texture information of microholes were obtained using fractal theory and machine vision techniques, including the gray-level co-occurrence matrix (GLCM) algorithm, image binarization, and edge extraction. A comprehensive numerical characterization of various microhole features was conducted, providing the basis for subsequent prediction and optimization. Secondly, the previously-extracted microhole features were set as input layer, and the processing parameters were set as output layer. After proper training, the BP neural network optimization model (GABPNN), based on the genetic algorithm, was established. As compared to the original BPNN model, the GABPNN model exhibited improved performance, reducing the maximum prediction error from 4.860% to 2.285%. Thirdly, with a set of input layer parameters, the required processing parameters were predicted by the model. The predicted results were verified in experiments, where good surface quality of the laser-drilled BMG microholes with good roundness and small ablation was obtained. This shows that it is feasible to predict and optimize processing parameters by GABPNN based on feature parameters extracted by machine vision.

Identification of Shale Lithofacies from FMI Images and ECS Logs Using Machine Learning with GLCM Features

The identification of sedimentary structures in lithofacies is of great significance to the exploration and development of Paleogene shale in the Boxing Sag. However, due to the scale mismatch between the thickness of laminae and the vertical resolution of conventional wireline logs, the conventional lithofacies division method fails to realize the accurate classification of sedimentary structures and cannot meet the needs of reservoir research. Therefore, it is necessary to establish a lithofacies identification method with higher precision from advanced logs. In this paper, a method integrating the gray level co-occurrence matrix (GLCM) and random forest (RF) algorithms is proposed to classify shale lithofacies with different sedimentary structures based on formation micro-imager (FMI) imaging logging and elemental capture spectroscopy (ECS) logging. According to the characteristics of shale laminae on FMI images, GLCM, an image texture extraction tool, is utilized to obtain texture features reflecting sedimentary structures from FMI images. It is proven that GLCM can depict shale sedimentary structures efficiently and accurately, and four texture features (contrast, entropy, energy, and homogeneity) are sensitive to shale sedimentary structures. To accommodate the correlation between the four texture features, the random forest algorithm, which has been proven not to be affected by correlated input features, is selected for supervised lithofacies classification. To enhance the model’s ability to differentiate between argillaceous limestone and calcareous mudstone, the carbonate content and clay content calculated from the ECS logs are involved in the input features. Moreover, grid search cross-validation (CV) is implemented to optimize the hyperparameters of the model. The optimized model achieves favorable performance on training data, validation data, and test data, with average accuracies of 0.84, 0.79, and 0.76, respectively. This study also discusses the application of the classification model in lithofacies and production prediction.

Machine vision assisted fused deposition modelling process optimization using grey level co-occurrence matrix

Taguchi's Design of Experiments was applied to determine the effect of Fused Deposition Modeling (FDM) parameters such as layer thickness, infill density, and infill line thickness and deposition pattern on surface roughness. Nylon material was fused to produce samples. Conventional probe surface area measurements were performed to extract the Ra values of the samples. Subsequently, the non-contact measurement of 3D printed textures using the Gray Level Co-Occurrence Matrix (GLCM) algorithm was introduced through image processing. The FDM-printed surface image parameters such as correlation and homogeneity are Ra responsive and therefore a signal-to-noise ratio (S/N) analysis was performed to identify optimal parameters. A slight, unexplained deviation in surface image parameters was detected, and this inaccurate deviation may be due to image noise, image distortion, and different lighting associated with capturing and processing printed surface images. The result of the analysis shows that a good surface quality is achieved if a layer thickness of 0.2 mm, 100% bulk density and 1.0 mm bulk thickness are selected. When optimal parameters were reached, the FDM print was repeated and then the results were validated to ensure the accuracy of the method used. The results obtained in the present study could be proposed in the field of additive manufacturing, which improves the surface quality of the FDM sample.

Pavement damage identification and evaluation in UAV-captured images using gray level co-occurrence matrix and cloud model

In the road structure, the pavement is in direct contact with the wheel, and its daily maintenance is very important. Traditional pavement damage detection relies heavily on manual work, which is inefficient and unsafe. In this paper, the unmanned aerial vehicle (UAV) is used to pick up the pavement damage image, and then combine the gray level co-occurrence matrix (GLCM) algorithm and the cloud model theory to construct a damage identification and evaluation model. In the experimental stage, a road in Chongqing, China is selected to verify the model. The results show that the accuracy of the proposed theoretical model in pavement damage identification exceeds 82.5%, and the performance is good. In addition, in the evaluation case, the lightest damage is the crack, and the most serious is the rut. For the hollow and block repair, the texture feature cloud droplet membership ratio of the two is mostly between 0.5 and 0.6, indicating that the damage state of the pavement is evolving from slight to moderate.

Quantitative Assessment of Hyperpigmentation Changes in Human Skin after Microneedle Mesotherapy Using the Gray-Level Co-Occurrence Matrix (GLCM) Method.

The aim of the study was to quantitatively assess the effectiveness of microneedle mesotherapy in reducing skin discoloration. The results were analyzed using the gray-level co-occurrence matrix (GLCM) method. The skin of the forearm (7 × 7 cm) of 12 women aged 29 to 68 was examined. Microneedle mesotherapy was performed using a dermapen with a preparation containing 12% ascorbic acid. Each of the volunteers underwent a series of four microneedle mesotherapy treatments. The effectiveness of the treatment was quantified using the methods of image analysis and processing. A series of clinical images were taken in cross-polarized light before and after a series of cosmetic procedures. Then, the treated areas were analyzed by determining the parameters of the gray-level co-occurrence matrix (GLCM) algorithm: contrast and homogeneity. During image pre-processing, the volunteers' clinical images were separated into red (R), green (G) and blue (B) channels. The photos taken after the procedure show an increase in skin brightness compared to the photos taken before the procedure. The average increase in skin brightness after the treatment was 10.6%, the average decrease in GLCM contrast was 10.7%, and the average homogeneity increased by 14.5%. Based on the analysis, the greatest differences in the GLCM contrast were observed during tests performed in the B channel of the RGB scale. With a decrease in GLCM contrast, an increase in postoperative homogeneity of 0.1 was noted, which is 14.5%.

Classification of COVID-19 from X-ray Images using GLCM Features and Machine Learning

As the world continues to battle the devastating effects of the COVID-19 pandemic, it has become increasingly crucial to screen patients for contamination accurately and effectively. One of the primary screening methods is chest radiography, utilizing radiological imaging to detect the presence of the virus in the lungs. This study presents a cutting-edge solution to classify COVID-19 infections in chest X-ray images by utilizing the Gray-Level Co-occurrence Matrix (GLCM) and machine learning algorithms. The proposed method analyzes each X-ray image using the GLCM to extract 22 statistical texture features and then trains two machine learning classifiers - K-Nearest Neighbor and Support Vector Machine - on these features. The method was tested on the COVID-19 Radiography Database and was compared to a state-of-the-art method, delivering highly efficient results with impressive sensitivity, accuracy, precision, F1-score, specificity, and Matthew's correlation coefficient. The proposed approach offers a promising new way to classify COVID-19 infections in chest X-ray images and has the potential to play a crucial role in the ongoing fight against the pandemic.

An Effective Supervised Machine Learning Approach for Indian Native Chicken’s Gender and Breed Classification

This study proposes a computer vision and machine learning (ML)-based approach to classify gender and breed in native chicken production industries with minimal human intervention. The supervised ML and feature extraction algorithms are utilized to classify eleven Indian chicken breeds, with 17,600 training samples and 4,400 testing samples (80:20 ratio). The gray-level co-occurrence matrix (GLCM) algorithm is applied for feature extraction, and the principle component analysis (PCA) algorithm is used for feature selection. Among the tested 27 classifiers, the FG-SVM, F-KNN, and W-KNN classifiers obtain more than 90% accuracy, with individual accuracies of 90.1%, 99.1%, and 99.1%. The BT classifier performs well in gender and breed classification work, achieving accuracy, precision, sensitivity, and F-scores of 99.3%, 90.2%, 99.4%, and 99.5%, respectively, and a mean absolute error of 0.7.

Development of a Fast Convergence Gray-Level Co-Occurrence Matrix for Sea Surface Wind Direction Extraction from Marine Radar Images

The new sea surface wind direction from the X-band marine radar image is proposed in this study using a fast convergent gray-level co-occurrence matrix (FC-GLCM) algorithm. First, the radar image is sampled directly without the need for interpolation due to the algorithm’s application of the GLCM to the polar co-ordinate system, which reduces the inaccuracy caused by image transformation. An additional process is then to merge the fast convergence method with the optimized GLCM so that the circular transition between rough and fine estimates is acquired, resulting in the fast convergence and accuracy improvement of the GLCM. Furthermore, the algorithm will affect the GLCM spatial distribution while calculating it, and it can automatically resolve the 180° ambiguity problem of sea surface wind direction retrieved from radar images. Finally, the proposed method is applied to 1436 X-band marine radar sequences collected from the coast of the East China Sea. Compared with in situ anemometer data, the correlation coefficient is as high as 0.9268, and the RMSE is 4.9867°. The new method was also tested under diverse sea conditions. The FC-GLCM wind direction results against the adaptive reduced method (ARM), energy spectrum method (ESM), and the traditional GLCM (T-GLCM) method produced the best stability and accuracy, in which the RMSE decreased by 91.6%, 67.7%, and 18.1%, respectively.

POMEGRANATE DISEASE DETECTION AND PESTICIDES SUGGESTION

Abstract: Pomegranate is a valuable fruit crop that is widely cultivated in various regions. However, its production is often threatened by various diseases that can significantly affect its yield and quality. In this project, we propose a method for pomegranate disease detection and pesticides suggestion using the gray-level co-occurrence matrix (GLCM) algorithm. The proposed approach utilizes GLCM to extract texture features from the pomegranate leaf images and classify them into healthy or diseased categories. Moreover, we suggest the most effective pesticides to control the detected diseases by using the GLCM algorithm. The performance of the proposed method is evaluated using a dataset of pomegranate leaf images with different disease symptoms. The experimental results demonstrate the effectiveness of our approach in detecting and classifying pomegranate diseases with high accuracy. Furthermore, the suggested pesticides show promising results in controlling the diseases. Overall, the proposed method can assist farmers in identifying pomegranate diseases at an early stage and provide appropriate suggestions for pesticide selection, which can reduce crop losses and enhance crop productivity. Keywords: classification, disease detection, GLCM algorithm.

Multi-Techniques for Analyzing X-ray Images for Early Detection and Differentiation of Pneumonia and Tuberculosis Based on Hybrid Features.

An infectious disease called tuberculosis (TB) exhibits pneumonia-like symptoms and traits. One of the most important methods for identifying and diagnosing pneumonia and tuberculosis is X-ray imaging. However, early discrimination is difficult for radiologists and doctors because of the similarities between pneumonia and tuberculosis. As a result, patients do not receive the proper care, which in turn does not prevent the disease from spreading. The goal of this study is to extract hybrid features using a variety of techniques in order to achieve promising results in differentiating between pneumonia and tuberculosis. In this study, several approaches for early identification and distinguishing tuberculosis from pneumonia were suggested. The first proposed system for differentiating between pneumonia and tuberculosis uses hybrid techniques, VGG16 + support vector machine (SVM) and ResNet18 + SVM. The second proposed system for distinguishing between pneumonia and tuberculosis uses an artificial neural network (ANN) based on integrating features of VGG16 and ResNet18, before and after reducing the high dimensions using the principal component analysis (PCA) method. The third proposed system for distinguishing between pneumonia and tuberculosis uses ANN based on integrating features of VGG16 and ResNet18 separately with handcrafted features extracted by local binary pattern (LBP), discrete wavelet transform (DWT) and gray level co-occurrence matrix (GLCM) algorithms. All the proposed systems have achieved superior results in the early differentiation between pneumonia and tuberculosis. An ANN based on the features of VGG16 with LBP, DWT and GLCM (LDG) reached an accuracy of 99.6%, sensitivity of 99.17%, specificity of 99.42%, precision of 99.63%, and an AUC of 99.58%.

Grey level co-occurrence matrix and learning algorithms to quantify and classify use-wear on experimental flint tools

Today, the analysis of use-wear traces of archaeological artefacts uses both qualitative (traditional) and quantitative (innovative) techniques. However, quantitative analyses require time and huge economic resources. It is important to find quantitative solutions that do not have high costs and that allow qualitative analysis to be more robust. Furthermore, quantitative analysis with 2D techniques would facilitate the standardization of the terms used to discriminate and describe the different types of polish.The Gray-Level Co-occurrence Matrix is a 2D image analysis technique that provides quantitative data on image texture. Although quite common in other research field, this technique has not been systematically applied in the archaeological research. Unlike other quantitative approaches this technique takes little time and has no cost, as it uses traditional 2D images. Futhermore, this method acts as a bridge between qualitative and quantitative analyses. In this first approach, four use-wear traces (unused, butchering, shell, wood, antler) on flint experimental samples were analysed with selections of square images of 300x300 and 600x600 pixels (30 for each contact material).This technique together with a learning algorithm called Support Vector Machine has proved effective in distinguishing and quantifying four types of use-wear traces.

Identification of cashmere and wool based on LBP and GLCM texture feature selection

There are invalid and redundant features in the texture feature extraction method of cashmere and wool fibers, which leads to the low recognition accuracy. In this paper, a novel texture feature selection method based on local binary pattern, the gray level co-occurrence matrix algorithm and chi-square test was proposed to sufficiently extract the effective features of these two fibers. Firstly, the collected images of cashmere and wool fibers are processed to obtain the clear texture images with background removed by pre-processing algorithm and local binary pattern. Then, the texture features are calculated by the gray level co-occurrence matrix, and the optimal 5-dimensional features are extracted by chi-square test to represent the texture information of cashmere and wool. Finally, the two fibers are automatically classified and recognized based on the support vector machine. The experimental results show that the proposed method obtained a high recognition accuracy with the percent of 94.39. It verifies that the method based on texture feature selection is effective to identify cashmere and wool fibers.

Investigation of Recognition and Classification of Forest Fires Based on Fusion Color and Textural Features of Images

An image recognition and classification method based on fusion color and textural features was studied. Firstly, the suspected forest fire region was segmented via the fusion RGB-YCbCr color spaces. Then, 10 kinds of textural features were extracted by a local binary pattern (LBP) algorithm and 4 kinds of textural features were extracted by a gray-level co-occurrence matrix (GLCM) algorithm from the suspected fire region. In terms of its application, a database of the forest fire textural feature vector of three scenes was constructed, including forest images without fire, forest images with fire, and forest images with fire-like interference. The existence of forest fires can be recognized based on the database via a support vector machine (SVM). The results showed that the method’s recognition rate for forest fires reached 93.15% and that it had a strong robustness with respect to distinguishing fire-like interference, which provides a more effective scheme for forest fire recognition.

Fault diagnosis method of bearing utilizing GLCM and MBASA-based KELM

In this study, fault diagnosis method of bearing utilizing gray level co-occurrence matrix (GLCM) and multi-beetles antennae search algorithm (MBASA)-based kernel extreme learning machine (KELM) is presented. In the proposed method, feature extraction of time–frequency image based on GLCM is proposed to extract the features of the bearing vibration signal, and multi-beetles antennae search algorithm-based KELM (MBASA-KELM) is presented to recognize the states of bearing. KELM employs the kernel-based framework, which has better generalization than traditional extreme learning machine, and it is necessary to look for an excellent optimization algorithm to select appropriate regularization parameter and kernel parameter of the KELM model because these parameters of the KELM model can affect its performance. As traditional beetle antennae search algorithm only employs one beetle, which is difficult to find the optimal parameters when the ranges of the parameters to be optimized are wide, multi-beetles antennae search algorithm (MBASA) employing multi-beetles is presented to select the regularization parameter and kernel parameter of KELM. The experimental results demonstrate that MBASA-KELM has stronger fault diagnosis ability for bearing than LSSVM, and KNN.

Detection and visualization of soybean protein powder in ground beef using visible and near-infrared hyperspectral imaging

The undeclared addition of soybean proteins in meats is a serious problem due to health and economic reasons. This paper proposes a methodology for quantitative determination and rapid visualization of soybean protein powder (SPP) addition in ground beef using hyperspectral imaging (HSI). Hyperspectral images of a total of 256 samples with different SPP contents were acquired by HSI system in spectral range of 400–1000 nm. Regions of interest (ROIs) were identified to withstand interference of background and containers to extract spectra. Principal component analysis (PCA) of extracted spectra found that PC1 and PC2 were effective for grouping samples into different levels. Gray level co-occurrence matrix (GLCM) algorithm was thus applied on the corresponding first two PC score images to extract eight texture features. Partial least squares regression (PLSR) was used to establish quantitative models, yielding the optimal correlation coefficient in prediction (Rp) of 0.9979 and residual predictive deviation (RPD) of 14.48 using standard normal variate (SNV) followed by detrending preprocessed spectra. Deming and Passing-Bablok regression were also conducted, and HSI results revealed high model performance which can be interchanged with laboratory standard. Key wavelengths were selected using PC loadings, two-dimensional correlation spectroscopy (2D-COS) and regression coefficients (RC), respectively. After that, PLSR models were evaluated with various inputs, and results showed spectra played predominate role rather than texture. Consequently, simplified PLSR model based on six selected wavelengths from PC loadings was retained with Rp = 0.9933, RPD = 8.45 and limit of detection (LOD) of 0.74%. Colorful spatial distribution maps were successfully created to clearly observe SPP adulteration levels. Current study indicates that HSI has high potential for determining and visualizing SPP adulteration in ground beef.

COVID-19 Diagnosis by Multiple-Distance Gray-Level Cooccurrence Matrix and Genetic Algorithm

COVID-19 is extremely contagious and has brought serious harm to the world. Many researchers are actively involved in the study of rapid and reliable diagnostic methods for COVID-19. The study proposes a novel approach to COVID-19 diagnosis. The multiple-distance gray-level co-occurrence matrix (MDGLCM) was used to analyze chest CT images, the GA algorithm was used as an optimizer, and the feedforward neural network was used as a classifier. The results of 10 runs of 10-fold cross-validation show that the proposed method has a sensitivity of 83.38±1.40, a specificity of 81.15±2.08, a precision of 81.59±1.57, an accuracy of 82.26±0.96, an F1-score of 82.46±0.88, an MCC of 64.57±1.90, and an FMI of 82.47±0.88. The proposed MDGLCM-GA-based COVID-19 diagnosis method outperforms the other six state-of-the-art methods.