Texture Classification Research Articles

Proximal sensor data fusion and auxiliary information for tropical soil property prediction: Soil texture

• Does combining proximal sensor always bring synergy for predicting soil texture? • Vis-NIR, NixPro TM , and pXRF data were tested for soil texture predictions. • PXRF provided key information to create accurate prediction models. • Smoothed Vis-NIR data preprocessing and dry NixPro TM condition positively influenced the results. • Soil texture and textural classes were accurately predicted by at least one approach. Soil texture is a primary variable influencing many soil chemical-physical-biological processes, providing important information for decision-making regarding sustainable soil management. The standard traditional methods for determining soil texture, however, are performed manually and are time-consuming, costly, and generate chemical wastes. As an alternative, portable X-ray fluorescence (pXRF) spectrometry and visible near-infrared spectroscopy (Vis-NIR) have been increasingly used worldwide to predict soil attributes. Other sensors (e.g., NixPro TM color sensor) are also promising, but less evaluated to date. Thus, investigations towards proximal sensor data fusion for prediction of soil textural separates (clay, silt, and total, coarse, and fine sand contents) and soil textural classes (loam, loamy sand, etc) in tropical soils are rare. Therefore, this study aimed to evaluate proximal sensor data for predicting soil particle size fractions and soil textural classes (both Family particle size classes and USDA soil texture triangle) via random forest algorithm in tropical regions. A total of 464 soil samples were collected from A (n = 208) and B (n = 256) horizons in Brazil. Soil samples were submitted to laboratory analyses for soil texture and proximal sensor (pXRF, Vis-NIR, and NixPro TM ) scanning. Samples were randomly split into 70% for modeling and 30% for validation. The best approach varied according to the predicted attribute; however, pXRF data were key information for soil texture prediction accuracy. The best results delivered highly accurate predictions via the aforementioned proximal sensors for rapid assessment of soil texture (total sand R 2 = 0.84, RMSE = 7.60%; silt 0.83, 6.11%; clay 0.90, 5.64%; coarse sand 0.87, 6.30%; fine sand 0.82, 5.27%). Categorical prediction accuracy for soil textural classes (Family particle size classes, overall accuracy = 0.97, Kappa index = 0.95; USDA soil texture triangle, 0.83, 0.73) was enhanced when the predictions were made by soil order sub-datasets. Smoothed Vis-NIR preprocessing and dry NixPro TM color data positively influenced the results. The results reported here represent alternatives for reducing costs and time needed for evaluating soil texture, supporting agronomic and environmental strategies in Brazilian conditions. Further works should extend the results of this study to temperate regions to corroborate the conclusions presented herein regarding the fusion of these three proximal sensors.

Comparison of color imaging vs. hyperspectral imaging for texture classification

Many approaches of texture analysis by color or hyperspectral imaging are based on the assumption that the image of a texture can be viewed as a multi-component image, where spatial interactions within and between components are jointly considered (opponent component approach) or not (marginal approach). When color images are coded in multiple color spaces, texture descriptors are based on Multi Color Channel (MCC) representations. By extension, a Multi Spectral Band (MSB) representation can be used to characterize the texture of material surfaces in hyperspectral images. MSB and MCC representations are compared in this paper for texture classification issues. The contribution of each representation is investigated with marginal and/or opponent component strategies. For this purpose, several relevant texture descriptors are considered. Since MSB and MCC representations generate high-dimensional feature spaces, a dimensionality reduction is applied to avoid the curse of dimensionality. Experimental results carried out on three hyperspectral texture databases (HyTexiLa, SpecTex and an original dataset extracted from the Timbers database) show that considering between component interactions in addition to the within ones significantly improves the classification accuracies. The proposed approaches allow also to outperform state of the art hand-designed descriptors and color texture descriptors based on deep learning networks. This study highlights the contribution of hyperspectral imaging compared to color imaging for texture classification purposes but also the advantages of color imaging depending on the considered texture representation.

Water retention and availability in Brazilian Cerrado (neotropical savanna) soils under agricultural use: Pedotransfer functions and decision trees

Soil water retention evaluation is critical for modeling water flow and solute transport in the vadose zone. The objectives of this study were to evaluate the performance of five data-fitting models for the soil water retention curve, to evaluate the performance of various pedotransfer functions for estimating model parameters, and to evaluate the use of decision trees for estimating water retention and availability in soil. Soil samples were collected from ten sites in the south-southwest central region of Mato Grosso State, in Brazil’s Cerrado biome (neotropical savanna). The sampling included five soil texture classes to determine the soil water retention curve (SWRC) and other soil properties. The mathematical description of SWRC was performed using the Brooks and Corey, Campbell, Libardi, Rogowski, and van Genuchten models. All models showed similar performance for matric potentials between −500 and −1500 kPa, while for higher potentials only the models of Brooks and Corey, Campbell and van Genuchten showed reasonable performance and were recommended for fitting the soil water retention curve from saturation to dryness. Among the best models, Campbell model showed lower performance for sandy soils, while van Genuchten model showed lower performance for sandy clay loam soils. Pedotransfer functions were created to estimate the parameters of the Brooks and Corey, Campbell, and van Genuchten models, but only the function fitted to the Brooks and Corey model showed adequate performance. Decision trees were created for estimating field capacity and permanent wilting point, thus providing a practical, easy-to-use tool that can be used as an alternative to pedotransfer functions in decision-making processes.

Petrogenetic and textural classification of kimberlites and lamproites of the Brauna Kimberlitic Field: Implications for potassic/ultrapotassic magmatism in the São Francisco Craton

Kimberlitic rocks are known in the São Francisco Craton, Brazil, since the 1980s when the De Beers started a prospective work in the Itapicuru River Greenstone Belt. However, 40 years later, the scientific knowledge about these occurrences is still very restricted. This paper presents new geological and petrographical data for the pipes of the “Brauna Kimberlitic Field”. These rocks are exposed in a strongly eroded cratonic area of Northeastern São Francisco Craton and as expected, represent the deepest parts of these bodies, showing textural aspects and components typical of coherent volcanic rocks emplaced at deep crustal levels.The kimberlitic magmatic event resulted not only in the emplacement of macrocrystalline hypabyssal olivine archetypal kimberlites, here represented by the B3 (678–682 Ma) and B4 pipes (s.s. Former type 1 kimberlites), but also in hypabyssal macrocrystalline pyroxene-phlogopite- lamproite intrusions, as exposed in the B7 (641 Ma) pipe of the Brauna Field. Both magmas are rich in mantle-xenoliths and have potential for diamond ores. The observed features suggest the presence of multiple magmatic pulses – which acted as deep samplers, recorded in the diversity of xenoliths and xenocrysts – thus demonstrating the potential of these rocks for the comprehension of the first stages of evolution of the Early Earth as well as for understanding the formation of the metasomatized lithospheric mantle below the São Francisco Craton.The new data for these hypabyssal facies, macrocrystic pulse of kimberlitic rocks in the Brauna Field, São Francisco Craton, Brazil, can be used to characterize the petrographic and mineralogical heterogeneities of a Neoproterozoic alkaline-ultrapotassic magmatic event that shows a kimberlite-lamproite transitional nature. The petrogenetic knowledge presented for the São Francisco Craton kimberlites and lamproites – accordingly to the most recent classifications for these rocks – include textural-genetic data, geotectonic environment, and intrusive-spatial context, setting these rocks at the stage 5 of present-day kimberlite classification scheme. Moreover, the integration of such data and the close spatial associations of kimberlites, lamproites, lamprophyres, syenites and shoshonites allowed to create a solid interpretation of the rock formation processes that correlates these Neoproterozoic alkaline ultrapotassic magmas to the reactivation of ancient mantle conduits in a thick lithosphere that overlies a previously metasomatized mantle and intrude a metal-rich craton environment.

The Dutch soil physical units map: BOFEK

Soils and their properties play an important role in land evaluation studies. Often such studies focus on larger scales ranging from watersheds up to the national scale or even larger. Soil properties are often known at smaller scales, sometimes at the level of individual soil samples. The aim of this study is to show how point information on soil hydraulic properties, i.e., water retention and hydraulic conductivity characteristics, can be upscaled via soil textural classes to a soil physical units map of a region or nation. Base information is the Dutch soil map (1:50,000) and the hydraulic properties of individual soil samples. All individual soil samples for which hydraulic properties were measured were divided based on their texture into eighteen top-soils and eighteen sub-soils. For each of these thirty-six groups geometric average water retention and hydraulic conductivity characteristics were derived. In total 368 derived soil profiles are distinguished in the Dutch soil map consisting of soil layers that are linked to the thirty-six texture groups. For each soil profile eight static hydraulic properties were calculated. The soil profiles were then clustered based on these properties into seventy-nine clusters or units, which then make up a soil physical units map for the Netherlands. It has been demonstrated that dynamically simulated transpiration reduction for the clustered situation is similar to obtained for all individual soil profiles. At the Dutch national scale, the difference in simulated transpiration reduction between runs using all 368 soil profiles or the 79 soil physical units was less than 2.5 % percentage-points in 96 % of all plots or less than 5 % percentage-points in 99 % of all plots. Similar good correspondence was obtained for other water balance terms as well, including actual transpiration, actual evaporation at the soil surface, degree of saturation at 15 and 30 cm depth, the integrated water flux at 100 cm depth and surface runoff.

ELGONBP: A grouped neighboring intensity difference encoding for texture classification

ELGONBP: A grouped neighboring intensity difference encoding for texture classification

Biochar Amendments for Reducing Nitrate Leaching from Soils of Different Textural Classes in the Nigerian Savanna

This study was carried out with the aim of assessing the effectiveness of four biochar materials; in reducing nitrate leaching from soils of three different textural classes in the Nigerian Savanna region. Soil samples (0-20 cm depth) were collected from three different soil types and three different locations each in the Nigerian Savanna using stratified random sampling. Two hundred and fifty (250) g of soil samples were amended with 0, 2.5, 5, 7.5 and 10 tonha-1 of Maize cob biochar (MCB), rice husk biochar (RHB), cow dung biochar (CDB) and poultry litter biochar (PLB) and were subjected to laboratory leaching experiment. Sixty (60) ml of nutrient solutions containing 300 mgl-1 nitrate using ammonium nitrate (NH4NO3) was applied to each of the laboratory biochar-incubated soil columns to study biochar effect on nutrients retention and transport. The experiment was laid in a Randomize Complete Block Design (RCBD) replicated three times. Leachates were collected and nitrate concentration was determined using a dual beam UV/VIS spectrophotometer. The data collected were analysed using the Generalized Linear Model (GLM) procedure and the means were separated using Tukey’s honest significant difference (SAS version 9.4). Results obtained revealed that there were no significant differences among the biochar treatments on nitrate leaching from Clay loam. However, highest nitrate leaching from Loamy soil of 30.53% was recorded by the application of 2.5 tonha-1 PLB and was significantly different from the application of 2.5 and 5-ton ha-1 RHB and 5-ton ha-1 MCB. Similarly, highest nitrate leaching from Sandy loam of 32.18 % was recorded by the application of 5-ton ha-1 MCB and was significantly higher than 5.94, 2.40 and 7.12 % recorded by the application of 2.5 and 5-ton ha-1 RHB and 7.5 tonha-1 CDB respectively. Therefore, application of 2.5, 5-ton ha-1 RHB and 7.5 tonha-1 CDB can effectively reduce nitrate leaching from Sandy loam. While 2.5, 5, 7.5 tonha-1 CDB and 2. 5 and 5 tonha-1 RHB reduced nitrate leaching from Loamy soils.

Correction to: Feature selection and mapping of local binary pattern for texture classification

Correction to: Feature selection and mapping of local binary pattern for texture classification

Visual assessment of soil structural quality across soil textures and compaction levels – Part I: Examination of intact soil cores

Soil structural degradation has become very common and leads to a serious decline in soil health. Improving or maintaining soil structure is key to build resilience against drought and flooding, and thus contributes to assuring food and water security. Quantification of soil structural quality is usually accomplished by traditional laboratory-based methods, which are time-, labour- and money-consuming. Visual soil evaluation and examination methods comprise rapid and simple tests that offer a numeric semi-quantitative assessment of soil structure. The common criteria are aggregate size and shape, ease of break or rupture resistance, and inter- or intra-aggregate porosity. In this study, the CoreVESS method, a variant of the Visual Evaluation of Soil Structure (VESS) method originally developed for topsoil assessment, was applied on 250 cm3 undisturbed soil core samples. Resulting soil quality scores (Sq, ranging between 1, good, and 5, poor) were compared with soil quality indicators (SQi) derived from traditional quantitative methods of soil structure analysis. Tested SQi’s included penetration resistance, bulk density, soil hydraulic properties, soil organic carbon and texture (percentage of clay, silt and sand). The objective of the study was to assess and quantify the state of soil structural degradation induced by agricultural operations using a suite of methods of analysis at a regional scale, with a special focus on CoreVESS. Soil core samples were taken in Belgium from 42 cropped fields, at two positions (headland and in-field zone) and from three layers, notably the ploughed topsoil (TOP, 10–20 cm), the compacted subsoil (CSUB, 30–40 cm) and the deeper subsoil (SUB, 60–70 cm), totalling the sample horizons to 252. Test and sampling sites comprised all major soil texture classes within the Belgian soil textural triangle and varied from sand to heavy clay. In-field positions (IN-FIELD) showed significantly better coreVESS-based Sq scores as compared to headland positions (HEAD), with the CSUB layers always exhibiting significantly lower quality than the other two layers. Laboratory-derived soil quality indicator (SQi) values portrayed the same trend, with CSUB layers always indicating the poorest soil quality. Significant differences in SQi’s were also found between soils of acceptable (Sq ≤ 3) and degraded (Sq > 3) structure. Likewise, grouping soils into the same categories resulted in significant differences in the soil water retention and hydraulic conductivity curves in their wet ranges. There were good significant relationships between the SQi values and CoreVESS-based Sq scores, with for example Pearson R correlation coefficients of 0.64 for both penetration resistance and bulk density. Also, Sq scores related well with an SQi-based soil quality index (SQI) value averaged per layer and texture class (Pearson R of 0.60). The study confirmed that agricultural operations and their intensity clearly affect soil structural quality across various soil textures, with CoreVESS being as responsive to variation in soil structure quality as traditional quantitative methods, even when applied in the subsoil. VESS methods thus have a potential for monitoring soil structural quality over a variety of textures in a rapid, intuitive, practical and cheap way, as an alternative for or being complementary to more expensive labour-intensive traditional quantitative methods.

Visual assessment of soil structural quality across soil textures and compaction levels – Part II: Examination of profile walls vs Intact soil cores

Visual Evaluation of Soil Structure (VESS) methods receive increasing attention and are gaining popularity. Since in modern agriculture, soil structure degradation becomes very common, it is essential to protect and improve soil structure quality. Methods that enable its straightforward monitoring are therefore needed. Numerous visual soil evaluation techniques that serve this purpose exist, and are varying in objective, evaluation depth (topsoil/subsoil), evaluation method, number of criteria assessed and their final scoring. In this study, we mainly focus on three VESS methods, two of which were employed in the field along a profile wall (Visual Evaluation of Subsoil Structure, SubVESS, and Double Spade VESS method, DSVESS), and one in the laboratory on soil cores (CoreVESS). The main aim of this research was to test and compare these VESS-based methods in terms of their feasibility and repeatability in detecting soil structure degradation in the topsoil and subsoil. Sixteen cropped fields were chosen in Belgium covering six of seven major soil texture classes according to the Belgian soil textural triangle (i.e., sand, loamy sand, light sandy loam, silt loam, clay, and heavy clay). SubVESS and DSVESS were performed in the same pits until 80 cm and 40 cm, respectively. Soil cores for CoreVESS and for the determination of soil quality indicators (SQi) with conventional laboratory methods were taken from three layers, that is, the ploughed topsoil (∼10–∼20 cm, “TOP”), the compacted subsoil (∼30–∼40 cm, “CSUB”), and the deeper subsoil (∼60–∼70 cm, “SUB”), totalling 96 horizons. While SubVESS and CoreVESS were originally developed to evaluate subsoil and topsoil, respectively, they were thus used here beyond those zones. Moreover, all sampling and field evaluation was done at two positions per field - the more compacted headland and the less compacted in-field zone. It was shown that the soil quality (Sq) scores assigned to the cores with CoreVESS were not significantly influenced by operators with different backgrounds but all having received basic VESS training. When comparing field and laboratory results, positive relationships were found between Sq scores of SubVESS, DSVESS and CoreVESS. All VESS methods were able to assign significantly better soil quality (lower scores) at in-field positions (IN-FIELD) as compared to headland positions (HEAD), and significantly lower quality (higher scores) to CSUB layers than to the other two layers. Laboratory-derived SQi values presented a similar trend, with CSUB layers always indicating worse situations. There were good significant relationships between the SQi values and the different VESS-based Sq scores as well, with DSVESS showing the best correlations among the three VESS methods. The study thus confirmed that the different VESS methods all have a potential for monitoring soil structure quality in a fast, cheap, intuitive and practical way, although they all have their own advantages and disadvantages. Additionally, those methods that were employed at depths other than those for which they were developed did perform well.

Repeatability and reproducibility of magnetic resonance imaging-based radiomic features in rectal cancer.

Purpose: Radiomics of magnetic resonance images (MRIs) in rectal cancer can non-invasively characterize tumor heterogeneity with potential to discover new imaging biomarkers. However, for radiomics to be reliable, the imaging features measured must be stable and reproducible. The aim of this study is to quantify the repeatability and reproducibility of MRI-based radiomic features in rectal cancer. Approach: An MRI radiomics phantom was used to measure the longitudinal repeatability of radiomic features and the impact of post-processing changes related to image resolution and noise. Repeatability measurements in rectal cancers were also quantified in a cohort of 10 patients with test-retest imaging among two observers. Results: We found that many radiomic features, particularly from texture classes, were highly sensitive to changes in image resolution and noise. About 49% of features had coefficient of variations in longitudinal phantom measurements. About 75% of radiomic features in in vivo test-retest measurements had an intraclass correlation coefficient of . We saw excellent interobserver agreement with mean Dice similarity coefficient of for test and retest scans. Conclusions: The results of this study show that even when using a consistent imaging protocol many radiomic features were unstable. Therefore, caution must be taken when selecting features for potential imaging biomarkers.

Efficient Propagation Methods and Management Implication of Aconitum chasmanthum Stapf ex Holmes: A Critically Endangered and Endemic Medicinal Herb of Kashmir Himalaya

Background: Knowledge about propagation of rare and endangered plant species is very important for their conservation and sustainable utilization. Therefore, it is imperative to understand different reproductive aspects of such species for their conservation and management. It is in this backdrop different propagation method of Aconitum chasmanthum- a Critically Endangered and Endemic Medicinal plant species has been undertaken. Methods: Seed germination was carried out using different media. For each treatment mean germination time (MGT) was also calculated. Different agro-techniques were also developed in different soil textural classes. The fresh underground tubers of the species were collected from natural population and were split longitudinally into 2, 3 and 4 pieces depending upon the size of the parental tuber containing a portion of shoot apex. The split cuttings were treated with 100 ppm IAA, IBA and GA3 for 48 hours and were sown in sandy loam soils under pots at Herbal Garden. The pots were kept in diffused light to monitor the leafy shoot generation, survival and comparison with the control (untreated cuttings). Result: The present study revealed that seeds of the species remain dormant for a pretty long period and do not germinate in darker conditions. Among various treatments the species showed 90.0±8.66% germination when chilled for 20 days with mean germination time (MGT) of 13.678±1.874 days as against 10.66±1.154% germination of the control. Although the plants grew nicely on various soils, maximum plant survival and vigorous growth was obtained in loamy textured soils. The plants responded to various nutrient treatments and in loamy soil the maximum dry biomass was shown by the plants treated with nitrogen (300 mg/kg soil) and NPK (500 mg/kg soil). The plants treated with NPK (500 mg/kg soil) produced 14.46±2.50 gm dry biomass as against the control of 5.23±0.750 gm per individual. The experimental manipulations also reveal that the species has a potential to propagate through tuber cuttings in sandy loam soils. The cuttings treated with IAA, IBA and GA3 showed 68.75% to 75.0% survival rate as against the 62.5% in control.

Detection of early decayed oranges by structured-illumination reflectance imaging coupling with texture feature classification models.

Citrus fruits are susceptible to fungal infection after harvest. To reduce the economic loss, it is necessary to reject the infected citrus fruit before storage and transportation. However, the infected area in the early stage of decay is almost invisible on the fruit surface, so the detection of early decayed citrus is very challenging. In this study, a structured-illumination reflectance imaging (SIRI) system combined with a visible light-emitting diode (LED) lamp and a monochrome camera was developed to detect early fungal infection in oranges. Under sinusoidal modulation illumination with spatial frequencies of 0.05, 0.15, and 0.25 cycles mm–1, three-phase-shifted images with phase offsets of − 2π/3, 0, and 2π/3 were acquired for each spatial frequency. The direct component (DC) and alternating component (AC) images were then recovered by image demodulation using a three-phase-shifting approach. Compared with the DC image, the decayed area can be clearly identified in the AC image and RT image (AC/DC). The optimal spatial frequency was determined by analyzing the AC image and pixel intensity distribution. Based on the texture features extracted from DC, AC, and RT images, four kinds of classification models including partial least square discriminant analysis (PLS-DA), support vector machine (SVM), least squares-support vector machine (LS-SVM), and k-nearest neighbor (KNN) were established to detect the infected oranges, respectively. Model optimization was also performed by extracting important texture features. Compared to all models, the PLS-DA model developed based on eight texture features of RT images achieved the optimal classification accuracy of 96.4%. This study showed for the first time that the proposed SIRI system combined with appropriate texture features and classification model can realize the early detection of decayed oranges.

Local Binary Patterns Based on Neighbor-Center Difference Image for Color Texture Classification with Machine Learning Techniques

This is a topic that receives a lot of interest since many applications of computer vision focus on the detection of objects in visually appealing environments. Information about an object’s appearance and information regarding the object’s motion are both used as crucial signals in the process of identifying and recognising any given item. This information is used to characterise and recognise the item. The identification of objects based solely on their outward appearance has been the subject of a substantial amount of research. However, motion information in the recognition task has received only a marginal amount of attention, despite the fact that motion plays an essential role in the process of recognition. In order to analyze a moving picture in a way that is both fast and accurate, it is required to make use of motion information in conjunction with surface appearance in a strategy that has been designed. Dynamic texture is a kind of visual phenomenon that may be characterised as a type of visual phenomenon that shows spatially repeated features as well as some stationary properties during the course of time by using methodologies that are associated with machine learning. The design of modern VLSI systems takes into consideration a larger chip density, which results in a processor architecture with several cores that are capable of performing a wide range of functions (multicore processor architecture). It is becoming more challenging to run such complicated systems without the use of electric power. In order to increase the effectiveness of power optimization strategies while maintaining system performance for text data extraction, it has been developed and put into practice power optimization strategies that are based on scheduling algorithms. Over the last twenty years, texture analysis has been an increasingly busy and profitable field of study. Today, texture interpretation plays a vital role in various activities ranging from remote sensing to medical picture analysis. The absence of tools to newline analyze the many properties of texture pictures was the primary challenge faced by the texture analysis approach. Texture analysis may be roughly categorised as texture classification, texture segmentation, texture synthesis, and texture synthesis. Texture categorization is useful in numerous applications, such as the retrieval of picture databases, industrial agriculture applications, and biomedical applications. Texture categorization relies on three distinct methods, namely, statistical, spectral, and structural methods. Statistical methods are based on the statistical characteristics of the image’s grey level. Features are collected using second order statistical order, autocorrelation function, and grey level co-occurrence matrix function.

Compact Hybrid Multi-Color Space Descriptor Using Clustering-Based Feature Selection for Texture Classification.

Color texture classification aims to recognize patterns by the analysis of their colors and their textures. This process requires using descriptors to represent and discriminate the different texture classes. In most traditional approaches, these descriptors are used with a predefined setting of their parameters and computed from images coded in a chosen color space. The prior choice of a color space, a descriptor and its setting suited to a given application is a crucial but difficult problem that strongly impacts the classification results. To overcome this problem, this paper proposes a color texture representation that simultaneously takes into account the properties of several settings from different descriptors computed from images coded in multiple color spaces. Since the number of color texture features generated from this representation is high, a dimensionality reduction scheme by clustering-based sequential feature selection is applied to provide a compact hybrid multi-color space (CHMCS) descriptor. The experimental results carried out on five benchmark color texture databases with five color spaces and manifold settings of two texture descriptors show that combining different configurations always improves the accuracy compared to a predetermined configuration. On average, the CHMCS representation achieves 94.16% accuracy and outperforms deep learning networks and handcrafted color texture descriptors by over 5%, especially when the dataset is small.

Neutrosophic set based local binary pattern for texture classification

This paper presents novel neutrosophic set-based Completed Local Binary Pattern (CLBP) hybrid methods. These methods first transform the input image into a neutrosophic domain, and the image's texture is characterized by truth and false membership components. Grayscale images are more robust to noise in the neutrosophic domain. The neutrosophic components suppress noise, by this way edges in the images may be detected more precisely. As a result, using neutrosophic truth and false sets with a grayscale input image has resulted in more robust features. Besides, these discriminative features are combined with rotation invariant LBP features with a cross-scale joint coding strategy. The proposed methods can contribute to the classification performance with a reasonable computational cost. When compared to state-of-the-art hand-crafted approaches, experimental findings on state-of-the-art texture databases show that the proposed methods can enhance classification accuracy by roughly 24%. Moreover, the proposed method achieves up to 34% better results than the state-of-the-art deep learning-based methods.

Feature selection and mapping of local binary pattern for texture classification

Feature selection and mapping of local binary pattern for texture classification

Spatial distribution characteristics of rare and endangered medicinal plant resources in Gansu province

Gansu province is located at the intersection of the three plateaus(Qinghai-Tibet Plateau, Inner Mongolia Plateau, and Loess Plateau) and the three river basins(Yellow River Basin, Yangtze River Basin, and inland river basin). The complex eco-environment and climate conditions here have created rich and diverse vegetation. Therefore, it is of great significance to study the spatial distribution characteristics of rare and endangered medicinal plant resources in Gansu province for formulating reasonable protection po-licies and promoting the development of medicinal plant industry. The data of rare and endangered medicinal plant resources in 87 counties of Gansu province were collected from results of the fourth general survey. The spatial distribution and the high-or low-value gathering area of rare and endangered medicinal plant resources in Gansu province were analyzed by geostatistical methods such as exploratory spatial data analysis, trend surface analysis, and Anselin Local Moran's I. The eco-environment characteristics of the high-or low-value gathering area were analyzed with the data of vegetation type, soil texture classification, annual mean temperature, annual mean precipitation, and elevation. Furthermore, the relationships of the spatial distribution and diversity with the geographical environment of rare and endangered medicinal plants in Gansu province were analyzed to provide support for the restoration and protection policy making of these plant resources.

Influence of Cold Plasma on Sesame Paste and the Nano Sesame Paste Based on Co-occurrence Matrix

The aim of the research is to investigate the effect of cold plasma on the bacteria grown on texture of sesame paste in its normal particle and nano particle size. Starting by using the image segmentation process depending on the threshold method, it is used to get rid of the reflection of the glass slides on which the sesame samples are placed. The classification process implemented to separate the sesame paste texture from normal and abnormal texture. The abnormal texture appears when the bacteria has been grown on the sesame paste after being left for two days in the air, unsupervised k-mean classification process used to classify the infected region, the normal region and the treated region. The bacteria treated with cold plasma, the time exposure is two minutes. The textural features related to gray level co-occurrence matrix are calculated for the normal, abnormal and the treated texture, it is obvious that the treated texture class has the best features compared with the other classes. The result shows the sesame paste treated with plasma has good result compared with nano sesame paste treated with plasma. This is because the plasma provides the sesame paste with heat and makes the sesame nano particle congregate together.

The response of finely textured and organic soils to lime and phosphorus application: Results from an incubation experiment

AbstractA soil's responses to phosphorus (P) input differs based on its chemical composition. Soil acidity and the presence of metallic cations dictate a soil's chemical composition. Currently, soil P application recommendations are universal and do not account for differing soil composition. A targeted soil‐specific approach is required to optimize P efficiency and availability. A pot incubation experiment was established to explore the effects of contrasting lime and P application rates across a range of soils (25), characterized by fine particle size and high levels of soil organic matter. Three contrasting rates of P were applied (0, 50, and 150 kg P ha−1) both with and without ground lime (CaCO3) at 5 tonne ha−1 over a 140‐day incubation period. The addition of lime buffered the soil, increasing nutrient availability and reducing P fixation. The 50 kg P ha−1 treatment rate was required to achieve sufficient plant available P in both mineral soil textural classes. Current legislative recommendations however do not allow the application of such rates, which has an impact on agronomic performance. Loam soils experienced a greater increase in M3 soil P in comparison to clay and organic soils. Organic soils posed a major threat to water quality due to poor P retention. A re‐evaluation of P recommendations is required to account for soil variability as current P allowances are insufficient on these particular soils.