Color Texture Research Articles

Research on texture features classification of multilayered wood flooring using global image structure method

ABSTRACT The manual classification method based on grain batch in multilayer wood-flooring-production line is inefficient and has a high false detection rate. In this study, a new algorithm combining the global-image structure (GIST) feature extraction technique with the Adaboost strategy integrated support vector Machine (SVM) is proposed. After preprocessing the image acquired by the CCD linear array camera, 12 groups of Gabor filters with different scales and directions were used, and the feature vector of the image was compressed by the average pooling method. Then the local linear embedding (LLE) algorithm was used to further reduce the feature dimension. Finally, the Adaboost strategy was used to integrate 10 support vector machines (SVMs) as classifiers, and the particle swarm optimization algorithm (PSO) was used for the hyperparameters of each SVMs. The accuracy of this method was 98.93%, and the three main evaluation parameters of F1 Score, Precision and Recall reached 99%, 100% and 98%, respectively. The texture feature-classification method adopted in this study effectively solves challenges caused by abnormal surface colour and complex texture, achieving remarkable results in multilayer solid-wood composite-flooring-texture classification.

Quality of Sous Vide-Cooked Pork Loin Stored in Refrigerated Conditions

The sous vide cooking method offers advantage in preparing meat dishes in advance. This study aimed to evaluate the effect of refrigerated storage on the quality attributes of pork loin sous vide cooked under selected, optimised temperature and time parameters. Pork loin was cooked at varying temperatures (57–63 °C) and times (3.5–5.5 h), followed by refrigerated storage for up to 7 days. Analytical methods, including TBARS index for lipid oxidation, instrumental colour measurement, texture analysis, and volatile compound profiling, were used to assess changes in meat quality over time. The results indicated that heat treatment and storage time significantly influenced lipid oxidation, colour, and texture. The highest TBARS values were observed at higher cooking temperatures (61 °C and 63 °C), reflecting increased lipid oxidation. Colour changes were also temperature- and time-dependent, with a decrease in redness (a*) and an increase in lightness (L*) and yellowness (b*). Sensory evaluation revealed that juiciness, aroma intensity, tenderness, and flavour acceptability were strongly correlated with overall acceptability, while physical characteristics like colour and texture had a lesser impact. The study highlights the impact of sous vide cooking parameters on the quality and sensory attributes of pork loin, suggesting that optimised heat treatment can help preserve desirable meat characteristics during refrigerated storage.

Predicting Color Development and Texture Changes in Tomatoes Treated With Hot Water and Exposed to High-Temperature Ethylene Using Support Vector Regression.

This study investigated the impacts of hot water treatment (HWT) at 50°C or 25°C for 5 min and high-temperature ethylene (HTE) exposure at varying temperatures (20°C, 30°C, or 35°C) and durations (24, 48, or 72 h) on the postharvest quality and antioxidant properties of mature green tomatoes (MG). Color changes, physicochemical characteristics, antioxidant compounds, and overall antioxidant ability were assessed. HWT increased β-carotene levels and oxygen radical absorbance capacity (ORAC) while preserving color metrics, despite later HTE exposure. Exposure to HTE delayed ripening, increased titratable acidity, and reduced dry matter content. The effects on antioxidant compounds varied depending on temperature and duration of exposure. A support vector regression (SVR) model predicted color parameters with high performance (R2 > 0.85) for lightness (L*), greenness-redness (a*), blueness-yellowness (b*), chroma, and hue values. The findings highlight the potential of HWT in postharvest quality management and underscore the complex interplay between HWT and HTE on tomato quality parameters.

Control of rotavirus by sequential stress of disinfectants and gamma irradiation in leafy vegetable industry.

Rotavirus (RV) causes severe gastroenteritis in infants and young children worldwide. Fresh produce has been reported as a source of RV infection during production and harvesting, leading to foodborne illness. Cases of contamination from contact surfaces have also been reported. Therefore, this study applied chemical methods (chlorine dioxide [ClO2], peracetic acid [PAA]), physical methods (gamma irradiation), and a combination of methods (disinfectants+gamma irradiation) to inactivate RV on food contact surfaces (stainless steel) and food (lettuce). Furthermore, the changes in food quality after the combined treatments were assessed. The results of the chemical treatment showed that RV was reduced below the detection limit after treatment for 1min with 20ppm ClO2 or 120ppm PAA in RV suspension. On stainless steel, treatment with 200ppm ClO2 or 2,000ppm PAA reduced contaminated RV by more than 4 log. A 5min treatment with 50ppm ClO2 or 80ppm PAA on lettuce reduced the RV by 1.79 and 0.75 log, respectively. Treatment with 4kGy of gamma irradiation resulted in more than 5 log reduction in suspensions and 3.27 log reduction on food. The sequential treatments, including 30ppm ClO2 followed by 1.5kGy gamma irradiation and 80ppm PAA followed by 1.5kGy gamma irradiation, showed additional inactivation effects (p<0.05) compared to each single treatment. No changes in food quality (color difference and texture) were observed after any treatments, suggesting that the combined treatment of both ClO2 and gamma irradiation and PAA and gamma irradiation can be applied in the fresh food industry to reduce RV contamination.

Statistical analysis of the proportion of recycled edible oil in the quality of scented candles

This work aims to analyze whether the variation in the proportion of recycled oil to make scented candles affects their quality. Three batches of candles were made at ratios 60-40, 70-30, and 80-20% of recycled oil and soy wax, respectively. The evaluation consisted of 7 tests: visual inspection, burning times, candle puddle, flame height, sensory rating scale, combustion afterglow check, combustion smoke, and post-combustion. The statistical analysis was performed using the MANOVA model. The multivariate test indicates a significant difference between the results of the quality tests of each batch of candles and the proportion used to manufacture the candles. However, the proportion of oil does not affect physical qualities such as color intensity, texture, imperfections, and aroma intensity.

OPTIMIZATION OF HPMC IN SERUM GEL CONTAINING BUTTERFLY PEA FLOWER EXTRACT (CLITORIA TERNATEA L.) AS FACIAL MOISTURIZER AND IT’S PHYSICAL STABILITY

Skincare refers to a series of skin treatments (epidermis) and the middle layer of the skin (dermis) aimed at protecting and maintaining the body, and is categorized as a cosmetic product. One of the most commonly used cosmetic preparations is skincare serum, which helps maintain skin elasticity and hydration. A rising trend in the industry is the development of serums, and one potential plant to be used as a safe active ingredient in cosmetics is the butterfly pea flower (Clitoria ternatea L), which is rich in flavonoids with antioxidant activity. The objective of this study was to determine whether butterfly pea flower extract serum can be formulated into a facial serum with moisturizing properties and to evaluate the physical stability of the serum preparation. The method used is Laboratory experiments were performed. The butterfly pea flower extract was obtained through maceration with 70% ethanol and then formulated into facial serum using different concentrations of HPMC base at 3%, 4%, and 5%. The results of serum stability tests were obtained using physical stability methods. Physical property tests included organoleptic testing (lavender scent, deep blue color, slightly thick, or serum-like texture), with stable organoleptic properties observed during storage, without any changes ...

First Report on the Emergence of Neopestalotiopsis rosae as a Severe Economic Threat to Strawberry Production in Germany.

Strawberries hold significant economic importance in both German and global agriculture. However, their yield is often adversely affected by fungal diseases. This study describes Neopestalotiopsis rosae as a newly emerging pathogen responsible for leaf blight and fruit rot in strawberries in Germany. Infected plants were observed in Hohenheim, Germany. A combination of morphological and molecular analyses, along with pathogenicity tests, confirmed the identity of N. rosae as the causal agent. Morphological examination of conidia and mycelium revealed key characteristics including the presence of versicolorous median cells, conidial appendages, black spherical conidiomata formation as well as changing colony color and fluffy texture. These properties align with the established descriptions for the species. Molecular analysis, particularly the sequencing of the internal transcribed spacer and β-tubulin regions allowed the precise identification of the pathogen. Artificial inoculation of healthy strawberry plants with conidial suspension derived from the isolated strain resulted in the development of characteristic symptoms, including necrotic leaf spots and water-soaked fruit lesions, similar to those observed on the original infected plants. To our knowledge, this study presents the first documented occurrence of N. rosae in Germany, highlighting its emergence as a significant threat to strawberry production in Europe.

An enhanced classification system of various rice plant diseases based on multi-level handcrafted feature extraction technique.

The rice plant is one of the most significant crops in the world, and it suffers from various diseases. The traditional methods for rice disease detection are complex and time-consuming, mainly depending on the expert's experience. The explosive growth in image processing, computer vision, and deep learning techniques provides effective and innovative agriculture solutions for automatically detecting and classifying these diseases. Moreover, more information can be extracted from the input images due to different feature extraction techniques. This paper proposes a new system for detecting and classifying rice plant leaf diseases by fusing different features, including color texture with Local Binary Pattern (LBP) and color features with Color Correlogram (CC). The proposed system consists of five stages. First, input images acquire RGB images of rice plants. Second, image preprocessing applies data augmentation to solve imbalanced problems, and logarithmic transformation enhancement to handle illumination problems has been applied. Third, the features extraction stage is responsible for extracting color features using CC and color texture features using multi-level multi-channel local binary pattern (MCLBP). Fourth, the feature fusion stage provides complementary and discriminative information by concatenating the two types of features. Finally, the rice image classification stage has been applied using a one-against-all support vector machine (SVM). The proposed system has been evaluated on three benchmark datasets with six classes: Blast (BL), Bacterial Leaf Blight (BLB), Brown Spot (BS), Tungro (TU), Sheath Blight (SB), and Leaf Smut (LS) have been used. Rice Leaf Diseases First Dataset, Second Dataset, and Third Dataset achieved maximum accuracy of 99.53%, 99.4%, and 99.14%, respectively, with processing time from [Formula: see text]. Hence, the proposed system has achieved promising results compared to other state-of-the-art approaches.

Induksi Kalus Krisan (Chrysanthemum morifolium var. reagen pink) dengan Penambahan Naphtalen Acetic Acid (NAA) dan Kinetin Secara In-Vitro

Chrysanthemum morifolium var. reagent pink is an ornamental flower that is widely cultivated in Indonesia. The increasing demand makes it difficult for farmers to fulfill the market. In-vitro tissue culture is an effective solution to multiply chrysanthemum seedlings in bulk and quickly. This study aims to identify the most effective concentration in inducing callus in chrysanthemum plants by combining Naphtalen Acetic Acid (NAA) and kinetin. This study was an experimental research with a completely randomized design (CRD), involving 12 treatments and each treatment was repeated 4 times. There were two treatment factors; NAA concentration (0 mg/l, 0.5 mg/l, 1 mg/l) and kinetin concentration (0 mg/l, 1 mg/l, 2 mg/l, 3 mg/l). Parameters in this study included days to callus appearance, percentage of callus explants, callus wet weight, callus color, and callus texture. Data were analyzed using analysis of variance (ANOVA). The results showed that (1) the fastest callus was formed at 11 HST by giving the treatment of 0 mg/l NAA + 3 mg/l kinetin; (2) the optimal treatment for the percentage of callus explants was obtained by giving 1 mg/l NAA + 1 mg/l kinetin); (3) the optimal treatment of callus wet weight was obtained by giving 1 mg/l NAA + 2 mg/l kinetin; (4) the best callus quality was obtained by giving a combination of NAA 1 mg/l and kinetin 1 mg/l, with a crumbly texture and brownish yellow callus.

Multi-objective classification prediction method for coal gangue based on image feature extraction

ABSTRACT Coal gangue is a solid waste discharged during the coal production process, consisting of rocks and minerals, and is a nonmetal mineral resource with attributes suitable for comprehensive utilization. This study explores the pre-classification issue of coal gangue comprehensive utilization through image recognition methods. Initially, coal gangue was categorized into four types – Residual coal, Gray gangue, Red gangue, and White gangue-based on its appearance, chemical composition, phase composition, and usage characteristics. Subsequently, the color features, texture features, and shape features of different types of coal gangue were analyzed using box plots, correlation coefficients, and cluster analysis. Finally, by comprehensively considering color, texture, and shape features, and by simplifying highly correlated variables, a support vector machine was employed for classification prediction. The overall recognition accuracy rate for multi-target classification reached 89%.

Influence of edible flowers on the physicochemical and oxidative stability of raw ground beef patties

This study investigates the antioxidant and physicochemical characteristics of raw ground beef patties and raw ground beef patties treated with varying percentages of roselle (Hibiscus sabdariffa L.) and rose (Rosa canina L.) powders during 7 days of storage at 4°C. The analysis included key parameters such as antioxidant activity using the 2,2-diphenyl-1-picrylhydrazyl (DPPH) assay, lipid oxidation through 2-thiobarbituric acid reactive substances (TBARS), protein oxidation markers (carbonyls, Schiff bases, and free thiols), water-holding capacity, pH, color, and texture. Both roselle and rose powders enhanced the antioxidant capacity of the patties, reducing oxidative markers (TBARS, carbonyls, Schiff bases, and free thiols) during storage. Additionally, improved water-holding capacity and reduced pH were observed across all treated patties, with minimal impact on texture. However, while roselle powder showed beneficial effects, patties treated with rose powder exhibited superior overall results. The more favorable outcomes in rose-treated patties, particularly in oxidative stability and physicochemical properties, can be attributed to the higher concentrations of bioactive compounds, such as phenolic acids and flavonoids, present in rose powder. These compounds likely contributed to enhanced free radical scavenging activity, providing stronger protection against lipid and protein oxidation. Furthermore, rose powder maintained more stable color and physicochemical properties, with patties showing acceptable color and minimal texture degradation by the 7th day of storage. These findings highlight the potential of rose powder as a highly effective natural additive for extending the shelf life and preserving the quality of ground beef patties, positioning it as a promising ingredient for future applications in the food industry.

Hybrid feature‐based moving cast shadow detection

AbstractThe accurate detection of moving objects is essential in various applications of artificial intelligence, particularly in the field of intelligent surveillance systems. However, the moving cast shadow detection significantly decreases the precision of moving object detection because they share similar motion characteristics. To address the issue, the authors propose an innovative approach to detect moving cast shadows by combining the hybrid feature with a broad learning system (BLS). The approach involves extracting low‐level features from the input and background images based on colour constancy and texture consistency principles that are shown to be highly effective in moving cast shadow detection. The authors then utilise the BLS to create a hybrid feature and BLS uses the extracted low‐level features as input instead of the original data. BLS is an innovative form of deep learning that can map input to feature nodes and further enhance them by enhancement nodes, resulting in more compact features for classification. Finally, the authors develop an efficient and straightforward post‐processing technique to improve the accuracy of moving object detection. To evaluate the effectiveness and generalisation ability, the authors conduct extensive experiments on public ATON‐CVRR and CDnet datasets to verify the superior performance of our method by comparing with representative approaches.

Comparison of Physical, Sensorial, and Microstructural Properties to Assess the Similarity Between Plant- and Animal-Based Meat Products

The aim of this study was to compare the physical, sensorial, and microstructural properties of selected meat products with their plant-based alternatives to assess how closely the alternatives mimic the original products. Six meat analogue products, including Frankfurter sausage (SuA), steak (StA), Hungarian sausage (KA), minced meat (MA), salami (SaA), and burger (BA), were compared with their corresponding meat products (SuM, StM, KM, MM, SaM, and BM, respectively). The study measured colour indicators, texture parameters, sensory attributes, and microstructural properties. The redness values (a*) of the external surfaces of SuM and KM, as well as the hardness of MM, were similar to those of their alternative products, with no statistically significant differences (p &gt; 0.05). Sensory evaluation revealed similar ratings for two attributes: product similarity and overall appearance. However, significant differences were found in the descriptors for animal character and meat taste.

Development of functional panela cheese enriched with prebiotics and probiotics

Food trends show interest in functional foods, which provide health and nutrition. This research is focused on developing a functional Mexican-style panela cheese that incorporates the probiotics Bifidobacterium animalis subsp. lactis, Lactobacillus delbrueckii subsp. bulgaricus NCFB 2772, Lacticaseibacillus rhamnosus GG and 4% inulin as a prebiotic. Yield, and content of lactic acid bacteria (LAB) and CFU of total coliforms were evaluated. Scanning Electron Microscopy was performed to evaluate the incorporation of the bacteria in the matrix. Furthermore, shelf life was established. The cheese yielded 26.6% (w/v), and its microbial content reached 7.12 × 10⁸ CFU/g, exceeding the Mexican Norm NOM 181. Inulin enhanced probiotic growth, and electron microscopy confirmed the successful integration of bacteria within the cheese matrix. Shelf-life studies demonstrated sustained LAB growth above 10⁸ CFU/g for 22 days, though the shelf life was determined to be 13 days under refrigeration at 4 °C due to coliform bacteria detection. Sensory evaluation revealed through just about right within the 60% range where dairy flavor, mouthfeel moisture, creaminess, and adhesiveness; showing that no reformulation should take place. Furthermore, CATA analysis showed that attributes that better described the product were dairy flavor, mouth moisture, fresh milk smell, white color, and smooth texture. The cheese scored 5.03 ± 1.23 on a 7-point acceptance scale and achieved a 69% purchase intention rate. Therefore, a functional cheese product was obtained with LAB and inulin with adequate sensory characteristics.

Prediction Method for Pomegranate Chlorophyll Content Based on Multi-feature Fusion of Unmanned Aerial Vehicle

The aim of this study was to obtain RGB and multispectral images of fruit tree canopy during the flowering period of pomegranate by multispectral unmanned aerial vehicle (UAV) to quickly and accurately predict the chlorophyll content in order to improve the monitoring efficiency of the orchard. A handheld chlorophyll meter was used to obtain the actual chlorophyll values, and image processing techniques were combined to extract parameters such as color features and texture features of the RGB images as well as vegetation index of the multispectral images. A chlorophyll content prediction method based on the support vector regression model and the convolutional neural network model (CNN-Attention) combined with the attention mechanism was established. The results showed that (1) the accuracy of the prediction model was improved by the fusion of RGB image features and multispectral image vegetation index. (2) After model comparison, the CNN-Attention model built under the fused features was the best in chlorophyll content prediction with R2, RE, and RMSE of 0.9699, 0.0052, and 0.6013, respectively.This study provides a more accurate method for fruit tree chlorophyll content prediction using UAVs, which provides a practical reference for orchard management.

Study of The Formulation Jicama Flour (Pachyrhizus erosus) and Wheat Flour on The Sensory Characteristics of Brownies Chips

Brownies chips is a meal made from brownies dough that is molded into thin squares and baked dry to produce chips that are easy to consume and last a long time. The aim of this research is to determine the formulation of jicama flour (Pachyrhizus erosus) and wheat flour which produces brownies chips with the best sensory properties on the attributes of color, scent, taste, texture, and overall acceptance. This research was structured in a Complete Randomized Block Design (RAKL) with six treatments and four replications. The formulation treatment of jicama flour and wheat flour consisted of 6 levels, namely T0 (0% : 100%), T1 (10% : 90%), T2 (20% : 80%), T3 (30% : 70%), T4 (40% : 60%), T5 (50% : 50%). Data were analyzed using the Bartlett test and Tukey test, followed by analysis of variance (ANARA), and the Least Significant Difference (BNT) test at the 5% level. Based on the research results, brownies chips with a formulation of jicama flour and wheat flour that produces the best sensory results is the T4 treatment which has a sweet and distinctive chocolate taste, blackish brown color, crunchy and dense texture, and aromatic. typical brownies chips. The results of the chemical analysis of the brownies chips were water content 3.76%, ash content 2.34%, protein content 13.87%, fat content 25.61%, carbohydrate content 54.42%, crude fiber content 6.01%. and calorific value are 503.65 kcal per 100 grams. The bengkuang flour can be used as a substitute up to 40% in the manufacture of brownie chips, producing products with good sensory quality and chemical content and has the potential as an alternative healthy snack.

Self - adaptive canny edge detection with reinforcement learning and dominant texture color patterns for melanoma segmentation and classification in dermoscopic images

Abstract Melanoma, considered to be the most rapidly increasing cancer, has had great emphasis placed on its diagnosis. This paper proposes a powerful edge detection framework Self-adaptive Canny Edge Detection using Reinforcement Learning (CRL-Edge) that integrates Canny edge detection with reinforcement learning. This approach adaptively fine-tunes the threshold parameters of the canny so as to enhance the edge continuity particularly for images with weak boundaries. The research also focusses on proposing a feature extraction method Dominant Texture Color Patterns (DTCP) that effectively helps in classifying malignant melanoma from dermoscopic images. This method is proposed based on the extraction of texture and color features that are dominant in a particular local region. The RGB color channel that consists of texture patterns with more intensity variations is said to be a dominant texture feature and a color channel that has maximum color intensity variations is a dominant color feature. The texture-color patterns are combined together to form a pattern that is assigned a unique texture-color value that describes the image features. The proposed feature of texture and color is analyzed in dermoscopic color images to classify lesions as benign or malignant, using CatBoost, a gradient boosting technique. The CatBoost is compared with other gradient boosting algorithms like Random Forest, XGBoost and Light GBM. The experiments were conducted on two different databases, the ISIC Archive and the PH2 database. The images were evaluated, on the basis of performance metrics such as sensitivity, specificity, accuracy, precision, F1-score and AUC. The experiment results show that CRL-Edge segmentation provides better segmentation accuracy and the DTCP descriptor using CatBoost classifier provides enhanced classification accuracy for classifying malignant lesion. The new method is compared with different state-of-art methods and has demonstrated the best performance.

Deep Fusion of Skeleton Spatial-Temporal and Dynamic Information for Action Recognition.

Focusing on the issue of the low recognition rates achieved by traditional deep-information-based action recognition algorithms, an action recognition approach was developed based on skeleton spatial-temporal and dynamic features combined with a two-stream convolutional neural network (TS-CNN). Firstly, the skeleton's three-dimensional coordinate system was transformed to obtain coordinate information related to relative joint positions. Subsequently, this relevant joint information was encoded as a color texture map to construct the spatial-temporal feature descriptor of the skeleton. Furthermore, physical structure constraints of the human body were considered to enhance class differences. Additionally, the speed information for each joint was estimated and encoded as a color texture map to achieve the skeleton motion feature descriptor. The resulting spatial-temporal and dynamic features were further enhanced using motion saliency and morphology operators to improve their expression ability. Finally, these enhanced skeleton spatial-temporal and dynamic features were deeply fused via TS-CNN for implementing action recognition. Numerous results from experiments conducted on the publicly available datasets NTU RGB-D, Northwestern-UCLA, and UTD-MHAD demonstrate that the recognition rates achieved via the developed approach are 86.25%, 87.37%, and 93.75%, respectively, indicating that the approach can effectively improve the accuracy of action recognition in complex environments compared to state-of-the-art algorithms.

STONE UTILISATIONS IN LANDSCAPE APPLICATION IN CRAIOVA CITY

In many ways stones are the bone of the earth. Stone in its many forms is a tangible, useful material that can find a place in every yard. The color selection, texture, cuts and paver size available will cater to any project for landscape. (Kristen Hampshire et al. 2009).In the beginning, the gardens had a utilitarian purpose, being made up of plants with a food role. Then the gardens take on the role of religious meditation, rest, culture and recreation. (Daniela Posta. 2015).Stone is a material that is born and evolves in nature as it is detached over time with stable, simple and almost primitive methods. Therefore, together with wood, it is undoubtedly the most suitable material for the formation of forest recreation areas, which are the most widespread means of human contact with nature and its beauties. The use of stone constructions in forest recreation is perfectly in harmony with the natural environment. Thus, people have the possibility to escape from the hectic rhythms of everyday life in forest recreation areas, relax and enjoy the forest through the conveniences offered by the stone constructions. (Vasileios C at al. 2023)

The Influence of Fermentation Technology on the Functional and Sensory Properties of Hemp Bread.

In this work, the type of fermentation and baking technology used to make hemp bread was investigated. The physicochemical composition of flour and bread, the protein nutritional quality, fatty acids profile, texture, consumer acceptance, analysis of volatile compounds using an electronic nose and chemical compounds using an electronic tongue were determined. Differences in protein and total dietary fiber content were observed in the obtained breads. The use of sourdoughs had a minor effect on the physical properties of the bread tested (the volume and mass of the loaves, color, or crumb texture). There was no clear effect of the tested sourdoughs on the parameters of the crumb texture and its moisture, assessed physically, both on the day of baking and during storage. In this bread, the limiting amino acid was lysine (amino acid score from 56.22% to 57.63%), but the breads did not differ significantly in the value of this indicator. The n-6/n-3 ratio in breads containing hemp flour (from 3.73 to 4.48) may have a beneficial effect on human health. The best-rated bread was the HB4 with a score of 6.09. The acceptance of remaining breads were in the range from 3.91 for HB1 to 4.91 for HB2.