Grayscale Co-occurrence Matrix Research Articles

Rock cutting image recognition based on color and texture feature fusion

Abstract In the realm of oil exploration, there is an increasing demand for precise lithological analysis, particularly in the rapid and accurate identification of fine rock cutting images. Therefore, a novel rock cutting image recognition method based on the fusion of color and texture features is proposed. This method utilizes the color histogram and grayscale co-occurrence matrix techniques to extract color and texture features from target images, respectively. Compared with the traditional single-feature recognition methods, this integrated feature method can greatly improve the accuracy of fragment recognition and ensure more accurate fragment classification by designing the feature fusion structure of the fragment image feature set. The model is established by using the support vector machine (SVM) classifier to realize the automatic classification and recognition of cuttings images. This not only reduces the time and labor intensity of manual operation, but also improves the efficiency and speed of cuttings analysis, which meets the needs of modern efficient drilling operations. More detailed and accurate stratigraphic data can be provided by high precision rock chip identification and lithology analysis. These data have important reference value for geologists to analyze stratigraphic structure and distribution, determine the location and distribution of underground oil and gas layers, and optimize drilling decisions and operation plans. Experimental results show that the method achieves an overall recognition accuracy of more than 90% in the task of detecting 126 rock chip images for conglomerate, 153 for mudstone, and 150 for sandstone, and up to 94% for mudstone and sandstone. It is proved that the recognition method proposed in this paper can better classify sandstone, mudstone and conglomerate in rock chips with high recognition accuracy.

Ensemble Machine-Learning-Based Framework for Estimating Surface Soil Moisture Using Sentinel-1/2 Data: A Case Study of an Arid Oasis in China

Soil moisture (SM) is a critical parameter in Earth’s water cycle, significantly impacting hydrological, agricultural, and meteorological research fields. The challenge of estimating surface soil moisture from synthetic aperture radar (SAR) data is compounded by the influence of vegetation coverage. This study focuses on the Weigan River and Kuche River Delta Oasis in Xinjiang, employing high-resolution Sentinel-1 and Sentinel-2 images in conjunction with a modified Water Cloud Model (WCM) and the grayscale co-occurrence matrix (GLCM) for feature parameter extraction. A soil moisture inversion method based on stacked ensemble learning is proposed, which integrates random forest, CatBoost, and LightGBM. The findings underscore the feasibility of using multi-source remote sensing data for oasis moisture inversion in arid regions. However, soil moisture content estimates tend to be overestimated above 10% and underestimated below 5%. The CatBoost model achieved the highest accuracy (R2 = 0.827, RMSE = 0.014 g/g) using the top 16 feature parameter groups. Additionally, the R2 values for Stacking1 and Stacking2 models saw increases of 0.008 and 0.016, respectively. Thus, integrating multi-source remote sensing data with Stacking models offers valuable support and reference for large-scale estimation of surface soil moisture content in arid oasis areas.

A Discriminative Model for Early Detection of Anthracnose in Strawberry Plants Based on Hyperspectral Imaging Technology

Strawberry anthracnose, caused by Colletotrichum spp., is a major disease that causes tremendous damage to cultivated strawberry plants (Fragaria × ananassa Duch.). Examining and distinguishing plants potentially carrying the pathogen is one of the most effective ways to prevent and control strawberry anthracnose disease. Herein, we used this method on Colletotrichum gloeosporioides at the crown site on indoor strawberry plants and established a classification and distinguishing model based on measurement of the spectral and textural characteristics of the disease-free zone near the disease center. The results, based on the successive projection algorithm (SPA), competitive adaptive reweighted sampling (CARS), and interval random frog (IRF), extracted 5, 14, and 11 characteristic wavelengths, respectively. The SPA extracted fewer effective characteristic wavelengths, while IRF covered more information. A total of 12 dimensional texture features (TFs) were extracted from the first three minimum noise fraction (MNF) images using a grayscale co-occurrence matrix (GLCM). The combined dataset modeling of spectral and TFs performed better than single-feature modeling. The accuracy rates of the IRF + TF + BP model test set for healthy, asymptomatic, and symptomatic samples were 99.1%, 93.5%, and 94.5%, the recall rates were 100%, 94%, and 93%, and the F1 scores were 0.9955, 0.9375, and 0.9374, respectively. The total modeling time was 10.9 s, meaning that this model demonstrated the best comprehensive performance of all the constructed models. The model lays a technical foundation for the early, non-destructive detection of strawberry anthracnose.

Synergizing the enhanced RIME with fuzzy K-nearest neighbor for diagnose of pulmonary hypertension

Pulmonary hypertension (PH) is an uncommon yet severe condition characterized by sustained elevation of blood pressure in the pulmonary arteries. The delaying treatment can result in disease progression, right ventricular failure, increased risk of complications, and even death. Early recognition and timely treatment are crucial in halting PH progression, improving cardiac function, and reducing complications. Within this study, we present a highly promising hybrid model, known as bERIME_FKNN, which constitutes a feature selection approach integrating the enhanced rime algorithm (ERIME) and fuzzy K-nearest neighbor (FKNN) technique. The ERIME introduces the triangular game search strategy, which augments the algorithm's capacity for global exploration by judiciously electing distinct search agents across the exploratory domain. This approach fosters both competitive rivalry and collaborative synergy among these agents. Moreover, an random follower search strategy is incorporated to bestow a novel trajectory upon the principal search agent, thereby enriching the spectrum of search directions. Initially, ERIME is meticulously compared to 11 state-of-the-art algorithms using the IEEE CEC2017 benchmark functions across diverse dimensionalities such as 10, 30, 50, and 100, ultimately validating its exceptional optimization capability within the model. Subsequently, employing the color moment and grayscale co-occurrence matrix methodologies, a total of 118 features are extracted from 63 PH patients' and 60 healthy individuals' images, alongside an analysis of 14,514 recordings obtained from these patients utilizing the developed bERIME_FKNN model. The outcomes manifest that the bERIME_FKNN model exhibits a conspicuous prowess in the realm of PH classification, attaining an accuracy and specificity exceeding 99%. This implies that the model serves as a valuable computer-aided tool, delivering an advanced warning system for diagnosis and prognosis evaluation of PH.

Experimental investigation of a fissured rock with thermal storage potential subjected to descending amplitude low cycle impacts

As the advancement of deep earth energy engineering in the 21st century, the challenges imposed by dynamic loads and high temperatures will be increasingly regular. This paper studied the dynamic mechanical behaviors and fracture characteristics of defective red sandstone (single fissure inclination of 0°, 30°, 60°, and 90°) subjected to thermal treatments (25 °C, 200 °C, 400 °C, 600 °C, and 800 °C) under descending amplitude low cycle (DALC) impact loading. The experiments were conducted using a modified split Hopkinson pressure bar (SHPB) system, and the fracture surfaces of the failed specimens were characterized through the use of high-resolution 3D laser scanning to obtain point cloud data. Subsequently, the fractal, roughness, texture, and elevation features of fracture surfaces were analyzed using the boxing-counting method, grayscale co-occurrence matrix (GLCM), and elevation-based statistics. The scanning electron microscopy (SEM) was utilized to study the fracture micromorphology as well. Additionally, the mechanisms of damage and fracture evolution were discussed based on the results of X-ray diffractometry (XRD), synchronous thermal analysis (STA), discrete element method (DEM), and strain energy density theory. The results demonstrate that the peak stress and dynamic elastic modulus deteriorate with rising temperatures and increase with larger fissure angles. While the peak strain, strain rate, and peak stress increase factor (PIF) exhibit the opposite trend. The threshold values for the intensification of these events are 400 °C and 60°. The damage is dominated by tensile cracks, which transition to shear at 30° and 60° due to temperature dependence. Meanwhile, the fractal dimension (DC), joint roughness coefficient (JRC), second-order statistics of GLCM, and elevation eigenvalues have been modeled using multiple regression analysis to investigate their interaction with temperature and fissure angle. The best-fit models illustrate significant linear or non-linear correlations between the aforementioned parameters and the mechanical parameters. Furthermore, the magnitude and distribution pattern of thermal cracks, as well as the growth of shear fractures, are governed by the dehydration, thermal expansion, phase transition, plasticization, thermal fracture, and thermal decomposition. Finally, strain energy density theory manifests promising prospects for understanding and predicting DALC impact fracture patterns of specimens.

Radial basis function Neural Network optimized with Salp Swarm algorithm espoused paddy leaf disease classification

Diseases in rice often cause yield losses of 20–40% in crop production and are closely linked globally. Disease detection is difficult to quickly plan treatments and decrease crop loss. Diagnosis of rice diseases till done manually. Attain AI-assisted detection of disease, here proposed radial function Neural Network optimized with Salp-Swarm approach (PLDC-RBFNN-SSA) for rice leaf disease segmentation. First, we extract rice leaf images from a dataset containing rice leaf disease image samples. Then the preprocessing augmentation process is performed using a random transformation method such as: Simple image rotation as well as mirror functions implemented to every images. B. Rotate Right 90°, Rotate Left 90°, Flip Vertically, Flip Horizontally, Rotate 180°. These preprocessed output images are then passed to Black Widow's k-means clustering method to segment regions of interest (ROI) for rice leaf disease. The segmented output image is then sent to an adaptive grayscale co-occurrence matrix windowing algorithm (GLCMWAA) to extract radiation features. Extracted features then input into a radial function Neural Network optimized with Salp-Swarm algorithm to classify rice leaf images into bacterial blight, blast, brown spot and tungro. The proposed method is implemented in MATLAB and the performance of the proposed PLDC-RBFNN-SSA approach achieves 15.25%, 18.98%, 20.5% and 24.85% higher accuracy. Computation time is reduced by 50.2%, 48.2%, 38.26%, 20.2% compared with existing methods. Finally, the simulation results demonstrate that the proposed PLDC-RBFNN-SSA method is more efficient and accurate to obtain the optimal global solution for detecting and classifying leaf diseases in rice breeding is shown.

Virtopsy visualisation: Mixed data gradient model for more accurate thin bone visualization in 3D rendering

Conventional 3D rendering methods of computed tomography (CT) as well as post-mortem data CT (PMCT) sometimes do not seem to be authentic enough, especially for relatively thin bones. This can be a problem when imaging intact anatomy and considering fractures of the facial or temporal bones, where defects or holes may be visualized instead of thin bone structures. The technical aspect of this is that all currently used visualization methods (volume rendering, cinematic rendering and particle tracing, shaded surfaces and iso-surfaces) are defined by a CT-density threshold, whereas the user at least implicitly expects the bone to have a certain minimum density CT. However, some bone regions, typically those with relatively thin bone, do not meet these expectations, and lowering the threshold for visualization then results in all sorts of non-bone tissue being seen in the rendered images. To provide a more authentic PMCT visualization of bone, we identified a mixed data gradient model that improves the data from CT by increasing the CT density of low-density bone regions (but not of non-bone tissues). That delivers more satisfactory results for otherwise unmodified volume rendering. As pre-processing before 3D rendering, both hard and soft kernel data are used to obtain a 3D density map, a grayscale co-occurrence matrix is determined using a 3x3x3 kernel as the 3D gradient map, and these are then combined to obtain the final gradient model for mixed data.

Machine Learning Assisting the Prediction of Clinical Outcomes following Nucleoplasty for Lumbar Degenerative Disc Disease.

Lumbar degenerative disc disease (LDDD) is a leading cause of chronic lower back pain; however, a lack of clear diagnostic criteria and solid LDDD interventional therapies have made predicting the benefits of therapeutic strategies challenging. Our goal is to develop machine learning (ML)-based radiomic models based on pre-treatment imaging for predicting the outcomes of lumbar nucleoplasty (LNP), which is one of the interventional therapies for LDDD. The input data included general patient characteristics, perioperative medical and surgical details, and pre-operative magnetic resonance imaging (MRI) results from 181 LDDD patients receiving lumbar nucleoplasty. Post-treatment pain improvements were categorized as clinically significant (defined as a ≥80% decrease in the visual analog scale) or non-significant. To develop the ML models, T2-weighted MRI images were subjected to radiomic feature extraction, which was combined with physiological clinical parameters. After data processing, we developed five ML models: support vector machine, light gradient boosting machine, extreme gradient boosting, extreme gradient boosting random forest, and improved random forest. Model performance was measured by evaluating indicators, such as the confusion matrix, accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC), which were acquired using an 8:2 allocation of training to testing sequences. Among the five ML models, the improved random forest algorithm had the best performance, with an accuracy of 0.76, a sensitivity of 0.69, a specificity of 0.83, an F1 score of 0.73, and an AUC of 0.77. The most influential clinical features included in the ML models were pre-operative VAS and age. In contrast, the most influential radiomic features had the correlation coefficient and gray-scale co-occurrence matrix. We developed an ML-based model for predicting pain improvement after LNP for patients with LDDD. We hope this tool will provide both doctors and patients with better information for therapeutic planning and decision-making.

Full-cycle data purification strategy for multi-type weld seam classification with few-shot learning

Weld seam type confirmation is a key part of intelligent integrated welding to cope with adjustable schemes varying with the seam morphology. However, existing works are mainly based on qualitative joint description (QJD) and machine learning classification (MLC), which entail high costs in balancing multiple given parameters, acquiring sufficient data and generalizing for new seam types. In this article, taking the advantages of few-shot learning, we propose a full-cycle data purification strategy (DPS) to identify seam types. First, five typical weld seams are mapped under three laser stripe patterns to acquire the raw samples. Then, a series of compliance processing algorithms are performed with reference to the target dataset to build a scenario dataset: purified weld seam stripe mapping (P-WSSM). With a few-shot learning pre-model, a positive weld seam classification result is obtained based on a small-volume dataset and analyze several critical factors. In addition, to compensate the application drawbacks caused by the wide randomness of low-volume datasets, compliance distance based on integrated grayscale co-occurrence matrix (I-GLCM) is introduced to quantitatively measure P-WSSM and the target dataset. Ultimately, experiments show that the dual-line stripe mapping achieves 85.4% recognition accuracy for 5-way 5-shot, which is a competitive multi-type weld seam classification via few-shot learning.

Optimal Time Phase Identification for Apple Orchard Land Recognition and Spatial Analysis Using Multitemporal Sentinel-2 Images and Random Forest Classification

The significance of identifying apple orchard land and monitoring its spatial distribution patterns is increasing for precise yield prediction and agricultural sustainable development. This study strived to identify the optimal time phase to efficiently extract apple orchard land and monitor its spatial characteristics based on the random forest (RF) classification method and multitemporal Sentinel-2 images. Firstly, the Normalized Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SAVI), Ratio Vegetation Index (RVI), and Difference Vegetation Index (DVI) between apple orchard land and other green vegetation (other orchards, forest and grassland) during the growing stage were calculated and compared to identify the optimal time phase for apple orchard land extraction; the RF classifier was then constructed using multifeature variables on Google Earth Engine to efficiently identify apple orchard land, and the support vector machine (SVM) classification results were used as a comparison; GIS spatial analysis, a slope calculation model, and Moran’s I and Getis-Ord GI* analysis were employed to further analyze the spatial patterns of the apple orchard land. The results found the following: (1) April, May, and October were the optimal time phases for apple orchard identification. (2) The RF-based method combining coefficients of indexes, the grayscale co-occurrence matrix, and 70% of the ground reference data can precisely classify apple orchards with an overall accuracy of 90% and a Kappa coefficient of 0.88, increasing by 9.2% and 11.4% compared to those using the SVM. (3) The total area of apple orchard land in the study area was 485.8 km2, which is 0.6% less than the government’s statistical results. More than half (55.7%) of the apple orchard land was distributed on the gentle slope (Grade II, 6–15°) and the flat slope (Grade I, 0–5°); SiKou, Songshan, and Shewopo contained more than 50% of the total orchard land area. (4) The distribution of apple orchard land has a positive spatial autocorrelation (0.309, p = 0.000). High–High cluster types occurred mainly in Sikou (60%), High–Low clusters in Songshan (40%), Low–High clusters in Sikou (47.5%), and Low–Low clusters in Taocun and Tingkou (37.4%). The distribution patterns of cold and hot spots converged with those of the Local Moran Index computation results. The findings of this study can provide theoretical and methodological references for orchard land identification and spatial analysis.

Experimental investigation on the fracture surface features of heat-treated red sandstone containing fissure under constant amplitude low cycle impact using 3D digital reconstruction

Fractured rocks as typical engineering materials are commonly exposed to temperatures and dynamic perturbations. In this paper, constant amplitude low cycle (CALC) impact tests were carried out on red sandstone containing a single fissure (0°, 30°, 60° and 90°) after thermal treatment (25 °C, 200 °C, 400 °C, 600 °C and 800 °C) utilizing a modified split Hopkinson pressure bar (SHPB). Subsequently, the fracture surfaces of the failure specimens were digitally reconstructed based on point cloud data captured by a three-dimensional (3D) laser scanning. And scanning electron microscopy (SEM) was also employed as a complementary tool to study the fracture micromorphology. The fractal and rough features of fracture surfaces based on the box-counting method and image segmentation method were investigated, respectively. Meanwhile, four second-order statistics in the grayscale co-occurrence matrix (GLCM) of the digitized fracture surface after grayscale processing were calculated to describe the fracture surface texture. The best-fit multiple regression models between the fracture surface feature parameters and the interaction of temperatures and fissure angles were constructed and analyzed. Moreover, the relationships between the fracture surface features and the mechanical parameters as well as the intrinsic mechanisms were analyzed and discussed in detail. The results demonstrate that the fractal dimension (DC), joint roughness coefficient (JRC), maximum elevation difference (MD), roughness characterization factor (ω), and GLCM second-order statistics possess specific response patterns to the temperatures and fissure angles. Whether the sensitivity in portraying the fracture surface features to the interaction of temperatures and fissure angles or the reliability of the best-fit multiple regression models, the shadow method based on image segmentation behaves more promisingly. Furthermore, conspicuous correlations can be found between both the feature parameters including the GLCM second-order statistics and the failure strength, strain rate as well as life. The high temperature activates thermal activation mechanisms that alter the potential crack sources and pathways in the grain and rock skeleton, affecting the microscopic fracture face morphology. Finally, the maximum tensile stress at the edge of the prefabricated fissure might be responsible for the angle effect exhibited by the feature parameters.

Estimation of potato above-ground biomass based on unmanned aerial vehicle red-green-blue images with different texture features and crop height

Obtaining crop above-ground biomass (AGB) information quickly and accurately is beneficial to farmland production management and the optimization of planting patterns. Many studies have confirmed that, due to canopy spectral saturation, AGB is underestimated in the multi-growth period of crops when using only optical vegetation indices. To solve this problem, this study obtains textures and crop height directly from ultrahigh-ground-resolution (GDS) red-green-blue (RGB) images to estimate the potato AGB in three key growth periods. Textures include a grayscale co-occurrence matrix texture (GLCM) and a Gabor wavelet texture. GLCM-based textures were extracted from seven-GDS (1, 5, 10, 30, 40, 50, and 60 cm) RGB images. Gabor-based textures were obtained from magnitude images on five scales (scales 1–5, labeled S1–S5, respectively). Potato crop height was extracted based on the generated crop height model. Finally, to estimate potato AGB, we used (i) GLCM-based textures from different GDS and their combinations, (ii) Gabor-based textures from different scales and their combinations, (iii) all GLCM-based textures combined with crop height, (iv) all Gabor-based textures combined with crop height, and (v) two types of textures combined with crop height by least-squares support vector machine (LSSVM), extreme learning machine, and partial least squares regression techniques. The results show that (i) potato crop height and AGB first increase and then decrease over the growth period; (ii) GDS and scales mainly affect the correlation between GLCM- and Gabor-based textures and AGB; (iii) to estimate AGB, GLCM-based textures of GDS1 and GDS30 work best when the GDS is between 1 and 5 cm and 10 and 60 cm, respectively (however, estimating potato AGB based on Gabor-based textures gradually deteriorates as the Gabor convolution kernel scale increases); (iv) the AGB estimation based on a single-type texture is not as good as estimates based on multi-resolution GLCM-based and multiscale Gabor-based textures (with the latter being the best); (v) different forms of textures combined with crop height using the LSSVM technique improved by 22.97, 14.63, 9.74, and 8.18% (normalized root mean square error) compared with using only all GLCM-based textures, all Gabor-based textures, the former combined with crop height, and the latter combined with crop height, respectively. Therefore, different forms of texture features obtained from RGB images acquired from unmanned aerial vehicles and combined with crop height improve the accuracy of potato AGB estimates under high coverage.

Detection of infestation by striped stem‐borer (Chilo suppressalis) in rice based on hyperspectral imaging

AbstractStriped stem‐borer (SSB) larvae are one of the most serious insect pests that damages rice. In this study, the combined hyperspectral imaging and chemometric method are proposed detect the early SSB larvae infestation in rice stems. Firstly, hyperspectral reflectance data (390–1040 nm) of rice stems were collected for normal, 3 days of infection, 6 days of infection, and 9 days of infection, respectively. On the spectra, the average spectra of the region of interest of the rice stalk samples were extracted, and 19 characteristic wavelengths were screened by the successive projection algorithm (SPA). Morphological processing was performed on the pseudo‐color (generally known as RGB) images of rice stalk samples on the images. Then five image texture features based on the gray‐scale co‐occurrence matrix (GLCM) and nine image color features based on color moments were obtained. The evaluation models of SSB larval infestation based on full spectra, characteristic wavelengths, GLCM, color moments, and data fusion were developed using partial least squares discriminant analysis (PLS‐DA), respectively. The results show that performance of the PLS‐DA model based on the fusion of characteristic wavelengths and GLCM is best. The accuracy of both the comprehensive modeling set and the prediction set is above 97%. The accuracy of the degree of infestation classification is good for all categories, and only the samples on the third day of infection are slightly less accurate. In conclusion, the hyperspectral imaging technology can be used to effectively detect the infection degree situation of early SSB larval infestation.Practical ApplicationsChemical control using insecticides to manage SSB infestation on rice is still the farmers' first choice. However, in the middle and late stages of rice growth, SSB larvae may moth into the inside of the rice stalk, and the rice provides a shelter for SSB so that the sprayed pesticides cannot reach SSB larvae, which produce a large number of overwintering SSB. This leads to the misuse of chemical pesticides, which causes serious pollution to the environment, pesticide residues also cause serious harm to the human body, and it also makes the pest resistance to pesticides rapidly increase. Therefore, it is necessary to find a rapid and effective detection method to detect the early infestation of SSB larvae on rice to reduce the use of pesticides and improve rice yield.

Interventions of Advanced Lung Cancer Patient Receiving Chemotherapy by Computed Tomography Image Information Data Analysis-Based Soothing Care Plans.

The objective of this study was to investigate the intervention effect of computed tomography (CT) image information data on patients with advanced lung cancer treated with chemotherapy under palliative care program. The research subjects were 60 patients with advanced lung cancer who received palliative care in our hospital from January 1, 2019, to January 1, 2021. All patients were grouped according to the evaluation criteria of solid tumor efficacy, including 28 patients in the remission group and 32 patients in the nonremission group. Texture analysis was performed on the CT images of the two groups of patients. The gray-scale cooccurrence matrix parameters, the maximum diameter of the lesion, and the CT value of the CT images of the two groups of patients before and after palliative care were compared. The results showed that after the palliative care, the combined mean, combined energy, and inverse moment of the three gray cooccurrence matrix parameters of the two groups of patients were decreased, and the combined entropy and contrast were increased. The absolute value of the gray-scale cooccurrence matrix Δ parameter of the patients in the remission group was greater than that in the nonremission group. The Δ combined entropy, Δ contrast, and Δ correlation of the two groups of patients were significantly different, and the difference in Δ contrast was the largest. It suggested that the gray-scale cooccurrence matrix parameter can evaluate the effect of soothing care, and the contrast was the best evaluation parameter. The maximum diameter of the lesions in the remission group before and after palliative care was reduced by 1.23 cm, and the degree of reduction was significantly better. The CT value was reduced by 6.22 HU, and the degree of reduction was significantly higher than that in the nonremission group. There was a significant difference in the data between the two groups (P < 0.05). Therefore, the CT image information data had a better evaluation effect on patients with advanced lung cancer under the palliative care program and can be applied to the clinical evaluation of the palliative care effect, which had good clinical value.

Feature extraction of partial discharge in low‐temperature composite insulation based on VMD‐MSE‐IF

Low-temperature composite insulation is commonly applied in high-temperature superconducting apparatus while partial discharge (PD) is found to be an important indicator to reveal insulation statues. In order to extract feature parameters of PD signals more effectively, a method combined variational mode decomposition with multi-scale entropy and image feature is proposed. Based on the simulated test platform, original and noisy signals of three typical PD defects were obtained and decomposed. Accordingly, relative moments and grayscale co-occurrence matrix were employed for feature extraction by K-modal component diagram. Afterwards, new PD feature vectors were obtained by dimension reduction. Finally, effectiveness of different feature extraction methods was evaluated by pattern recognition based on support vector machine and K-nearest neighbour. Result shows that the proposed feature extraction method has a higher recognition rate by comparison and is robust in processing noisy signals.

Application of Multitask Joint Sparse Representation Algorithm in Chinese Painting Image Classification

This paper presents an in-depth study and analysis of Chinese painting image classification by a multitask joint sparse representation algorithm for texture feature extraction of Chinese painting images and proposes a method to extract texture features directly for the original images. It simplifies the process of image grayscale conversion and preserves the information contained in the original Chinese painting images to the greatest extent. The algorithm uses the ideas of multicolor domain analysis and multiscale analysis, combined with the traditional grayscale coeval matrix to extract texture features. Experiments show that the multiscale grayscale cooccurrence matrix algorithm outperforms the traditional grayscale cooccurrence matrix algorithm and the color grayscale cooccurrence matrix algorithm. The discriminative ability of multiple features for target recognition is integrated by multitask learning, thus improving the robustness and generalization ability of the algorithm; meanwhile, the recognition accuracy is improved by using a two-level multitask learning mode to exclude the interference of a large number of irrelevant dictionary atoms. The experimental results show that the algorithm has higher recognition accuracy and better robustness than the existing sparse representation SAR target recognition algorithm. Configuration recognition experiments are conducted on different configurations of target data, and the experimental results show that the algorithm achieves better configuration recognition accuracy than existing algorithms.

Research on Application of Improved Random Forest in Medical Ultrasound Image Classification

Gray-scale ultrasound imaging methods are commonly used to assess synovitis in Rheumatoid Arthritis (RA) in clinical practice. This paper proposed an improved classification algorithm for ultrasound image of metacarpophalangeal joint in Rheumatoid Arthritis(RA). Using several features of gray scale co-occurrence matrix and improved Random Forest method to achieve automatic classification of Rheumatoid Arthritis(RA). Three grading experiments were carried out in the experiment: the first one is for the binary classification of grade 0 (normal) and grade 3 (lesion) ultrasound images of 80 × 50 pixels, 130 × 70 pixels, and 185 × 90 pixels. The second is for the binary classification of grade 0 (normal) and grade 1/2/3 (lesion) ultrasound images of 80 × 50 pixels, 130 × 70 pixels, and 185 × 90 pixels. The third is for four-grade classification of ultrasound images at grade 0(normal), grade 1(mild), grade 2(moderate), and grade 3(severe). Conclusion shows that use the method of combing gray scale co-occurrence matrix and improved Random Forest algorithm can achieve automatic classification of Rheumatoid Arthritis(RA), which has a high Classification Accuracy.

Diagnosis of the Severity of Fusarium Head Blight of Wheat Ears on the Basis of Image and Spectral Feature Fusion.

Fusarium head blight (FHB), one of the most prevalent and damaging infection diseases of wheat, affects quality and safety of associated food. In this study, to realize the early accurate monitoring of FHB, a diagnostic model of disease severity was proposed based on the fusion features of image and spectral features. First, the hyperspectral image of FHB infected in the range of the 400–1000 nm spectrum was collected, and the color parameters of wheat ear and spot region were segmented based on image features. Twelve sensitive bands were extracted using the successive projection algorithm, gray-scale co-occurrence matrix, and RGB color model. Four texture features were extracted from each feature band image as texture variables, and nine color feature variables were extracted from R, G, and B component images. Texture features with high correlation and color features were selected to participate in the final model building parameters via correlation analysis. Finally, the particle swarm optimization support vector machine (PSO-SVM) algorithm was used to build the model based on the diagnosis model of disease severity of FHB with different combinations of characteristic variables. The experimental results showed that the PSO-SVM model based on spectral and color feature fusion was optimal. Moreover, the accuracy of the training and prediction set was 95% and 92%, respectively. The method based on fusion features of image and spectral features can accurately and effectively diagnose the severity of FHB, thereby providing a technical basis for the timely and effective control of FHB and precise application of a pesticide.

Segmentation of Brain Tumor using Glcm and Discrete Wavelet Transform

To identify brain tumors at an early stage is a challenging task. The brain tumor is usually diagnosed with Magnetic Resonance Imaging (MRI). When MRI spectacles a tumor in the brain, the most common way of determining the type of brain tumor after a biopsy or surgery is to look at the results of a tissue sample. In this research to detect brain tumors faster and accurately the feature extraction techniques are used to segment the tumor affected area. One of such very effective technique of feature extraction measure is the Grayscale Co-occurrence Matrix (GLCM). This research focuses on the GLCM and Discrete Wavelet Transformation (DWT) technique to detect and label the tumor from an image based on the textures and categorizing it according to a tumor or non-tumor category. The convolutional neural network (CNN) uses these features to improve the accuracy to 91%.

Application of time-frequency image feature extraction method based on gray level co-occurrence matrix in coal mine pipeline leakage detection

The underground mining environment of coal mine is complex. Once the water supply or gas supply pipes leak, the location and time of leakage are unpredictable. If the leakage can not be found in time, it will seriously threaten the life safety of underground workers. Therefore, it is very necessary to automatically detect the pipeline leakage. In order to solve the problem of automatic detection of coal mine pipeline leakage, this paper proposes an image processing method based on gray level co-occurrence matrix to extract the features of time-frequency image of vibration signal. Firstly, the data in a relatively short time is divided into one frame to reduce the amount of calculation. Secondly, each frame of signal is processed by SPWVD to get the time-frequency image. Then, the time-frequency image after time-frequency analysis is transformed into gray-scale image, and the gray-scale co-occurrence matrix (GLCM) of the image is extracted. Finally, the energy, contrast and correlation of the co-occurrence matrix are extracted and input to SVM for learning and training. Through the design and build of the experimental pipeline to test the algorithm proposed in this paper, the detection result of SVM is 96.67%, which shows that this method can effectively detect the pipeline leakage.