Color Classification Research Articles

ETNOSEMANTIK DALAM KLASIFIKASI KAIN TENUN MASYARAKAT BIMA

Indicates that it is closely related to the perspective, social status, traditions and customs of the local community. Therefore, it is interesting to research in more depth from the linguistic and cultural aspects. The aim of this research is to describe the lexemes used to label woven fabrics in the Bima community and explain the cultural views of the local community which are reflected in the lexemes for woven fabrics in the Bima community. The research method used is descriptive qualitative with data collection using interviews, documentation and observation. The results of the research show that there are five types of woven fabric based on the yarn used, namely tembe nggoli kabali, tembe galendo, tembe salungka, tembe mesrais, and tembe kafa na'e, while there are 15 types of woven fabric based on motifs, including tembe salungka nggusu waru, tembe salungka karai cepe, tembe salungka kabate oi moti, tembe salungka ante fare, tembe salungka fu'u ringi dan pariah, tembe salungka kakando, tembe salungka dumu kakando, tembe salungka coma kapi, tembe salungka mada sahe, tembe salungka kapempe, tembe salungka raba, tembe salungka nasi, tembe salungka uma lengge, tembe salungka bunga satako, and tembe salungka kapi keu. In the color category of Bima woven cloth there are nine colors, namely yellow, green, blue, black, white, red, brown, purple and orange. For the community, lace weaving is an activity that must be carried out by every woman in this village, of all ages, regardless of their status and educational background.

A Study on Foundation Color Classification with the Application of Personal Colors

Purpose: The purpose of this study was to classify foundation colors by applying personal colors and then was to figure out the consistency in base and brightness between the personal color system (PCS) foundation colors with the face and skin color measurement and the self-diagnosis foundation colors.Methods: The research subjects included 40 women aged 20–50 years who lived in capital area. The data were analyzed with frequency and percentage analysis, χ<sup>2</sup>-test, and one-way ANOVA, <i>t</i>-test using SPSS WIN 27.0.Results: The foundation colors were inspected according to a personal color type. Consequently, the foundation colors appeared to be the Warm (Yellow) base as a type of spring and autumn of being sorted into Warm tone type, the Cool (Pink) base color as a type of summer and winter of being categorized into Cool tone, No. 21 brightness as a type of spring and summer, and No. 23 brightness as a type of autumn and winter.Conclusion: The results of this study can be considered to be what the PCS foundation color classification is available through the personal color application and to be what the outcome on women’s self-diagnosis foundation color measurement increases the availability of PCS foundation color classification. These findings arranged a theoretical ground on the skin color expression suiting themselves and on color matching through applying personal colors when women select foundation colors and are expected to be likely used as basic data in beauty field.

Classification of Apple Color and Deformity Using Machine Vision Combined with CNN

Accurately classifying the quality of apples is crucial for maximizing their commercial value. Deep learning techniques are being widely adopted for apple quality classification tasks, achieving impressive results. While existing research excels at classifying apple variety, size, shape, and defects, color and deformity analysis remain an under-explored area. Therefore, this study investigates the feasibility of utilizing convolutional neural networks (CNN) to classify the color and deformity of apples based on machine vision technology. Firstly, a custom-assembled machine vision system was constructed for collecting apple images. Then, image processing was performed to extract the largest fruit diameter from the 45 images taken for each apple, establishing an image dataset. Three classic CNN models (AlexNet, GoogLeNet, and VGG16) were employed with parameter optimization for a three-category classification task (non-deformed slice–red apple, non-deformed stripe–red apple, and deformed apple) based on apple features. VGG16 achieved the best results with an accuracy of 92.29%. AlexNet and GoogLeNet achieved 91.66% and 88.96% accuracy, respectively. Ablation experiments were performed on the VGG16 model, which found that each convolutional block contributed to the classification task. Finally, prediction using VGG16 was conducted with 150 apples and the prediction accuracy was 90.50%, which was comparable to or better than other existing models. This study provides insights into apple classification based on color and deformity using deep learning methods.

VI SUAL AND NOMINATIVE SIGNS OF CHARACTERS IN MARI NON-FABULOUS PROSE

: The text considers the visual appearance of demonic characters in the modern Mari folklore. Based on the texts of non-fabulous prose (bylichka, byvalschina), the author explores the manifestations of otherness in the descriptions of “evil spirits”: iya, keremet, ovda, targyltysh, revenants. The research focuses on models of describing the images of the Mari evil spirits, their visual characteristics and liminality in folklore narratives. The author considers the categories of color, size and other attributes as characteristics marking demonic folklore characters as chthonic. The work is based on field materials collected in places of compact residence of the Mari population in 2017–2022 (the Mari El Republic, the Kirov oblast’, the Republic of Bashkortostan). The work was carried out in an interdisciplinary manner, based on a combination of ethnographic and folkloristic scientific methods. The main scholarly direction addressed by the researcher is a semiotic approach to the study of myth and folklore, that is, a view of folklore texts and images as a sign system of concepts. The author combines the methods of field research, interviewing, narrative analysis, as well as the typological method. According to the author, in the description of “evil spirits” by informants several models of representation can be distinguished: anthropomorphic, anthropomorphic with hyperbolized features, zoomorphic, abstract. Special attention in the article is paid to the nominative features of characters in oral texts. The res earcher noted a tendency of informants to neutralize category of a folklore character.

Interior Scene Coloring Design Model Combining Improved K-means and SAA

Due to technological progress and changes in people’s aesthetic standards, traditional design models need to be constantly broken through, seeking more efficient and accurate design methods. Seeking effective design models to improve design efficiency and prediction accuracy is an important task. Therefore, this study proposes an indoor scene coloring design model that combines improved K-means clustering and simulated annealing algorithm for this important task. Based on the analysis of indoor scene coloring, particle swarm optimization algorithm is used to optimize K-means clustering to achieve color classification. Combined with simulated annealing algorithm, adaptive adjustment of lighting conditions is achieved to enhance the naturalness and realism of coloring. These results confirmed that the proposed method had the highest average F-value, with an average F-value of 92.524 and 143.601 on both datasets, respectively. The average ARI values were 0.361 and 0.897, respectively. The designed algorithm performed the best and converged faster than other three. Therefore, the proposed method can effectively ensure the consistency between the distribution of data objects after clustering and the actual situation. For indoor scene coloring design, it has important practical significance and provides new possible paths for improving design efficiency and prediction accuracy.

Increasing magnitude of color differences amplifies category effects

Previous studies have identified differences in sensitivity characteristics between color discrimination and perception of suprathreshold color differences. However, it remains highly unclear how color difference sensitivity changes with increasing magnitudes of color difference along various color hues. This study aimed to quantify the sensitivity transition across various magnitudes of color differences and uncover the underlying mechanisms. Color discrimination sensitivities were measured using an adaptive staircase method for 32 isoluminant pedestal colors in the u'v' chromaticity diagram. For suprathreshold color differences, we employed the Maximum Likelihood Difference Scaling (MLDS) method to measure sensitivity to various color difference levels for the same 32 colors. Our findings confirmed the differences in sensitivity characteristics between discrimination and suprathreshold color difference perception. Furthermore, we observed increased sensitivities at many color category boundaries in suprathreshold color difference perception. By investigating the relation between the category effects and the color difference size levels through a model simulation, our findings suggest that the influence of color categories on the perception of color differences may become more pronounced as the magnitude of color differences increases.

External location inhibits the spatial association for luminance

ABSTRACT This study explored luminance as magnitude stimulus to systematically investigate how the Simon effect influences the spatial associations of magnitude stimuli across tasks. The results showed that (1) the SNARC effect was absent in the magnitude stimuli across location , color and magnitude classification tasks and (2) the Simon effect was stable across these tasks. In addition, the SNARC effect and the Simon effect did not interact across these tasks. The results imply that the spatial associations of magnitude stimuli are inhibited by the magnitude stimuli locations when the location and magnitude information overlap.

Application of DMSFNN-COA technique for brand image design

Color plays a pivotal role in product design, as it can evoke emotional responses from users. Understanding these emotional needs is crucial for effective brand image design. This paper introduces a novel approach, the Brand Image Design using Deep Multi-Scale Fusion Neural Network optimized with Cheetah Optimization Algorithm (BID-DMSFNN-COA), for classifying product color brand images as “Stylish” and “Natural”. By leveraging deep learning techniques and optimization algorithms, the proposed method aims to enhance brand image accuracy and address existing challenges in product color trend forecasting research. Initially, data are collected from the Mnist Data Set. The data are then supplied into the pre-processing section. In the pre-processing segment, it removes the noise and enhances the input image utilizing master slave adaptive notch filter. The Deep Multi-Scale Fusion Neural Network optimized with cheetah optimization algorithm effectively classifies the product colour brand image as “Stylish” and “Natural”. Implemented on the MATLAB platform, the BID-DMSFNN-COA technique achieves remarkable accuracy rates of 99 % for both “Natural” and “Stylish” classifications. In comparison, existing methods such as BID-GNN, BID-ANN, and BID-CNN yield lower accuracy rates ranging from 65 % to 85 % for “Stylish” and 65 %–70 % for “Natural” product color brand image design. The simulation outcomes reveal the superior performance of the BID-DMSFNN-COA technique across various metrics including accuracy, F-score, precision, recall, sensitivity, specificity, and ROC analysis. Notably, the proposed method consistently outperforms existing approaches, providing higher values across all evaluation criteria. These findings underscore the effectiveness of the BID-DMSFNN-COA technique in enhancing brand image design through accurate product color classification.

Greenhouse gas emissions and their driving factors among different flowering Chinese cabbage (Brassica campestris L.) varieties.

Crop cultivars have an influence on greenhouse gas (GHG) emissions, and there is variation between varieties. However, there are few reports available on the differences in GHG emissions and their driving factors among vegetable varieties. In this study, we conducted a field experiment to examine the variances in GHG emissions and their contributing factors among eight flowering Chinese cabbage varieties (considering growth period, leaf shape, and colour). The results showed significant differences in GHG emissions within varieties; early-maturing varieties exhibited GHG by 25.6% and 15.3%, respectively, when compared to mid- and late-maturing varieties. Among the different leaf types and color classifications, light-colored and sharp-leafed varieties had the lower global warming potential (GWP) overall. Cumulative CO2 emissions were influenced by leaf SPAD values and biomass, while cumulative N2O emissions were driven mainly by stem thickness, carbon accumulation, leaf SPAD values, and biomass. In summary, the selection of light-colored varieties with pointed leaves and shorter growth periods in actual production contributed positively to the reduction of carbon emissions from flowering Chinese cabbage production. Through efficient variety screening, this study provides a win-win strategy for achieving efficient vegetable production while also addressing the global climate challenge.

A smartphone image-based method for the colorimetric characterization of historical pigments in mural paintings

In this article, the detailed description of a smartphone-based analytical method to turn a smartphone into a colorimeter is described and applied to mural painting replicas. The method consists of a camera characterization process, to estimate CIELAB values from RGB camera responses, correcting for potential experimental interferences, like the effect of the lighting/capture geometry or software for color modification and enhancement. Next, the estimated CIELAB descriptors were used to build a chemometric Support Vector Classifier to objectively distinguish among the colors of the different pigments. The method was validated in terms of color reproduction and classification performance.•A smartphone-based method is described to capture mural painting color.•A color gamut-specific camera characterization procedure is developed and the performance of the smartphone-based colorimeter is compared with a spectrophotometer.•A classification method based on the estimated CIELAB descriptors is validated in terms of classification performance.

Alternative methodology of special coffee roasting in the electric popcorn maker

The aim was to develop and evaluate an alternative method for roasting coffee, using a domestic electric popcorn machine, estimating an ideal roasting time to obtain a drink of high quality. The experiment was conducted under laboratory conditions, with 10 treatments, with roasting times ranging from 3 to 8 minutes. Grain mass reduction and roasting color classification, according to the ABG Agtron scale, were evaluated. Roasting was carried out in a domestic electric popcorn maker, from Mondial brand, model PP-04, with a power of 1200W. Time intervals of five to six minutes showed better coffee characteristics, medium roasting point, ideal for specialty coffees. The use of the popcorn machine as a coffee roaster showed a satisfactory result, since in a short period of time, it provided a uniform roast, which attributes superior quality, compared to conventional coffee found on the market.

Developing a Colorimetrically Balanced, Measurement-Based Petal Colour System for Cultivated Rose (Rosa L. Cultivars) and the Resulting Colour Categories.

There is no practical and at the same time objective colour system available for describing cultivated roses (Rosa L. cultivars). For this reason, a new colour classification system was developed which is colorimetrically balanced and appropriate for algorithmic colour identification; however, it is also suitable for field-work. The system is based on the following colorimetric criteria: (A) Each colour category is characterised by a measured petal colour in the CIE L*a*b* standard as the centroid of the category. (B) The CIEDE2000 colour differences between the adjacent centroid colours are limited (5 < ΔE00 < 7). (C) The maximal colour difference between the measured colours in a category is also limited (to 12.12 ΔE00). (D) A measured petal colour can only be classified into an existing category if the colour difference from the centroid colour of the given category is less than 5.81 ΔE00, otherwise a new category is required. (E) A category is only considered non-redundant if it has at least one measured petal colour that cannot be classified elsewhere. (F) The classification of the petal colours is based on the least colour difference from the centroid colours. As a result, 133 colour categories were required for describing all the 8139 petal colours of the rose cultivars of the Budatétény Rose Garden (Hungary). Each colour category has the following parameters: standardised colour name, the colorimetric parameters of the centroid, grouping, RHS colour chart coding, and reference cultivars, which are described in the article.

Tradescantia response to air and soil pollution, stamen hair cells dataset and ANN color classification.

Tradescantia plant is a complex system that is sensible to environmental factors such as water supply, pH, temperature, light, radiation, impurities, and nutrient availability. It can be used as a biomonitor for environmental changes; however, the bioassays are time-consuming and have a strong human interference factor that might change the result depending on who is performing the analysis. We have developed computer vision models to study color variations from Tradescantia clone 4430 plant stamen hair cells, which can be stressed due to air pollution and soil contamination. The study introduces a novel dataset, Trad-204, comprising single-cell images from Tradescantia clone 4430, captured during the Tradescantia stamen-hair mutation bioassay (Trad-SHM). The dataset contain images from two experiments, one focusing on air pollution by particulate matter and another based on soil contaminated by diesel oil. Both experiments were carried out in Curitiba, Brazil, between 2020 and 2023. The images represent single cells with different shapes, sizes, and colors, reflecting the plant's responses to environmental stressors. An automatic classification task was developed to distinguishing between blue and pink cells, and the study explores both a baseline model and three artificial neural network (ANN) architectures, namely, TinyVGG, VGG-16, and ResNet34. Tradescantia revealed sensibility to both air particulate matter concentration and diesel oil in soil. The results indicate that Residual Network architecture outperforms the other models in terms of accuracy on both training and testing sets. The dataset and findings contribute to the understanding of plant cell responses to environmental stress and provide valuable resources for further research in automated image analysis of plant cells. Discussion highlights the impact of turgor pressure on cell shape and the potential implications for plant physiology. The comparison between ANN architectures aligns with previous research, emphasizing the superior performance of ResNet models in image classification tasks. Artificial intelligence identification of pink cells improves the counting accuracy, thus avoiding human errors due to different color perceptions, fatigue, or inattention, in addition to facilitating and speeding up the analysis process. Overall, the study offers insights into plant cell dynamics and provides a foundation for future investigations like cells morphology change. This research corroborates that biomonitoring should be considered as an important tool for political actions, being a relevant issue in risk assessment and the development of new public policies relating to the environment.

Active Language Modulates Color Perception in Bilinguals

AbstractColor terms divide the color spectrum differently across languages. Previous studies have reported that speakers of languages that have different words for light and dark blue (e.g., Russian siniy and goluboy) discriminate color chips sampled from these two linguistic categories faster than speakers of languages that use one basic color term for blue (e.g., English blue). This effect has been reported to be disrupted when participants engaged in a verbal interference task, suggesting that active language use can modulate the linguistic category effect. The current study provided a stringent test of this hypothesis by examining color discrimination under verbal interference in bilinguals speaking Lithuanian (two blue categories) and Norwegian (one blue category). The results revealed that the language activated during verbal interference had a significant impact on bilinguals’ color discrimination. Specifically, Lithuanian–Norwegian bilinguals exhibited a color category effect only when performing the task under verbal interference in Lithuanian but not in Norwegian. This demonstrated, within the same individuals, the momentary effect of active language processing on color perception.

A Novel Laboratory Technique for Measuring Grain‐Size‐Specific Transport Characteristics of Bed Load Pulses

AbstractAlthough several laboratory studies on the propagation of bed load pulses were carried out in the last decades, most studies neglect grain‐size‐specific aspects or use invasive measurement techniques. To remedy the situation, we present a novel, time‐efficient and non‐destructive laboratory technique to investigate grain‐size‐specific transport characteristics of bed load pulses. The method consists of a through‐water, high‐resolution image acquisition followed by the application of a supervised color classification algorithm (Gaussian Maximum Likelihood Classification). The analyzed bed load pulse consisted of five different grain size classes of dyed quartz sand and gravel, each having a unique color. The initial experimental bed was uni‐colored and contained the same size fractions as the augmented pulse. Quality assessment based on a confusion matrix approach and basic random sampling showed a high classification performance. By statistically analyzing the temporal and spatial color distribution of the experimental reach, characteristic parameters to describe the propagation behavior were determined. The bed load pulse presented in the application example initially showed strong deviations in the grain‐size‐specific advection and dispersion, and advection proved to be predominant in the transport process.

Rapeseed Seed Coat Color Classification Based on the Visibility Graph Algorithm and Hyperspectral Technique

Information technology and statistical modeling have made significant contributions to smart agriculture. Machine vision and hyperspectral technologies, with their non-destructive and real-time capabilities, have been extensively utilized in the non-destructive diagnosis and quality monitoring of crops and seeds, becoming essential tools in traditional agriculture. This work applies these techniques to address the color classification of rapeseed, which is of great significance in the field of rapeseed growth diagnosis research. To bridge the gap between machine vision and hyperspectral technology, a framework is developed that includes seed color calibration, spectral feature extraction and fusion, and the recognition modeling of three seed colors using four machine learning methods. Three categories of rapeseed coat colors are calibrated based on visual perception and vector-square distance methods. A fast-weighted visibility graph method is employed to map the spectral reflectance sequences to complex networks, and five global network attributes are extracted to fuse the full-band reflectance as model input. The experimental results demonstrate that the classification recognition rate of the fused feature reaches 0.943 under the XGBoost model, confirming the effectiveness of the network features as a complement to the spectral reflectance. The high recognition accuracy and simple operation process of the framework support the further application of hyperspectral technology to analyze the quality of rapeseed.

Long-Term Comparison of Esthetic Outcomes Between Hatchet and Transposition Flaps in Facial-Defect Reconstruction.

Transposition flaps are commonly used for facial-defect repair after wide excision of skin cancers. However, such repair often causes excessive tension at the donor site that can result in distortion of the adjacent area. The hatchet flap, a rotation-advancement flap, can prevent distortion by redistributing the donor site tension evenly to the recipient site. This study aims to compare the esthetic outcomes of the hatchet flap and transposition flap in facial-defect reconstruction. We retrospectively included 50 patients who underwent facial reconstruction with the hatchet flap or transposition flap after excision of skin cancer. They were followed up for more than 6months. At the last follow-up visit, the esthetic outcome was evaluated by subjective and objective assessments using the patients and observer scar assessment scale and Manchester scar scale. Thirty patients and 20 patients underwent reconstruction using the hatchet flap and the transposition flap, respectively. The total score from the patient and observer scar assessment scale was significantly lower in the hatchet flap group compared with the transposition flap group (p = 0.009). The Manchester scar scale showed a total score of 7.67 ± 2.2 for the hatchet flap and 9.95 ± 1.99 for the transposition flap: in the color (p < 0.001), distortion (p < 0.001), and texture (p < 0.02) categories, the hatchet flap yielded significantly better outcomes than the transposition flap. The hatchet flap had good esthetic outcome for facial reconstruction and could be a valuable option for reconstructing facial defects. This journal requires that authors assign a level of evidence to each article. For a full description of these evidence-based medicine ratings, please refer to Table of Contents or online Instructions to Authors www.springer.com/00266.

Exploration Study of Contemporary Batik Motif at The Handayani Community Learning Center Kemirian Village Tamanan District Bondowoso Regency

The learning center community for public named Handayani is an Small and Medium Enterprise located in Kemirian Village, Tamanan Subdistrict, Bondowoso Regency. PKBM handayani is a non-formal educational institution and also known as a batik business that produces written batik, stamped batik, and semi batik. This study aims to identified any typical Motif of contemporary batik Bondowoso whose produced by PKBM Handayani. This research was using a qualitative descriptive approach with observation, interviews, and documentation both offline and online as the data collection techniques. The result for this research are the identification of nine Motifs of batik which consist by the classification of ornaments and colors, and also the symbols and meanings contained in the Motifs. This research also shows that the role of Bondowoso Regency government has been held well in the development of PKBM Handayani implemented as a facilitator, motivator, and catalyst. The researcher hopes that through this research, PKBM Handayani can be recognized and being widely known by the wider community and also increase its sales and their business development.

Color discrimination repetition distorts color representations

Perceptual learning is the improvement of perceptual performance after repeated practice on a perceptual task. Studies on perceptual learning in color vision are limited. In this study, we measured the impact of color discrimination repetitions at a specific base color on color perception for entire hues. Participants performed five sessions of color discrimination training (200 or 300 trials per session) over five days, at colors on either the negative or positive direction of the L-M color axis, based on group assignment. We administered three color perception assessments (unique hues, color category boundaries, and color appearance) before and after the sessions to evaluate perceptual changes after training. The results showed declines in color discrimination thresholds after training, as expected. Additionally, the training influenced outcomes across all three assessment types. After the training, the perceived color appearance changed near the trained color along the stimulus hue, and some of the unique hues and the color category boundaries moved significantly toward the trained color. These findings indicate that short-term repetitions of color discrimination training can alter color representations in the visual system, distorting color perception around the trained color.

Why we should have a universal air quality index?

Air pollution is known to be one of the major risk factors for premature morbidity and mortality globally, which are preventable. Therefore, the public is informed about air pollution through the Air Quality Index (AQI). The AQI represents integrated data of selected pollutants and produces a combined overall index for specific locations and time. The AQI algorithm generates a range of numbers and categories of colors that indicate likely health risks from air pollutants and the public's actions to minimize the risks. However, it lacks emerging evidence on chemical toxicity or composition. Hence, policymakers may also consider addinga toxicity matrix of fine particles to refine the algorithm, such as oxidative potential. Further, the risk is commonly communicated in numbers and not in color as dictated by the AQI. The AQI values and categories vary significantly between countries for the same pollution concentration, leading to confusion. Hence, we recommend developing a universal AQI (UAQI) with a consistent relationship between colors, concentrations, and toxicity to communicate air pollution risks to the public. Further, communication media should be encouraged to use universal color-coding rather than AQI values, i.e., numbers. Therefore, a global policy framework for regulatory authorities and policymakers is needed to communicate air pollution risk information consistently and to minimize public health exposure.