Color Space Research Articles

Classification of Vase Life Day Based on Petal Colorimetric Data in Cut Lisianthus Using AutoML

This study investigated the potential of petal colorimetric data to classify vase life stages in cut lisianthus flowers (Eustoma grandiflorum). We analyzed the changes in the petal color space over time, focusing on the b* value as an indicator of senescence due to increasing yellowing caused by copigmentation. A comparative analysis was conducted between two cultivation methods: soil (S) and hydroponic (H) cultivation. The objective was to evaluate the performance of machine learning models trained to classify vase life stages based on petal color data. Automated machine learning models exhibited better performance in H-cultivated cut flowers, effectively distinguishing days within the vase life stages from Days 1 to 14 for H cultivation. Cut flowers cultivated under S conditions showed less variation in the color space from Days 1 to 9, maintaining a relatively uniform color range. This made it more difficult to distinguish the vase life stages compared to H cultivation. These findings demonstrate that petal color metrics can serve as reliable indicators of cut flower senescence and potentially facilitate nondestructive methods for classifying vase life stages. This technology holds promise for wider applications in the floriculture industry, improving quality control, and extending the vase life of various cut-flower crops.

Effectiveness of data-augmentation on deep learning in evaluating rapid on-site cytopathology at endoscopic ultrasound-guided fine needle aspiration

Rapid on-site cytopathology evaluation (ROSE) has been considered an effective method to increase the diagnostic ability of endoscopic ultrasound-guided fine needle aspiration (EUS-FNA); however, ROSE is unavailable in most institutes worldwide due to the shortage of cytopathologists. To overcome this situation, we created an artificial intelligence (AI)-based system (the ROSE-AI system), which was trained with the augmented data to evaluate the slide images acquired by EUS-FNA. This study aimed to clarify the effects of such data-augmentation on establishing an effective ROSE-AI system by comparing the efficacy of various data-augmentation techniques. The ROSE-AI system was trained with increased data obtained by the various data-augmentation techniques, including geometric transformation, color space transformation, and kernel filtering. By performing five-fold cross-validation, we compared the efficacy of each data-augmentation technique on the increasing diagnostic abilities of the ROSE-AI system. We collected 4059 divided EUS-FNA slide images from 36 patients with pancreatic cancer and nine patients with non-pancreatic cancer. The diagnostic ability of the ROSE-AI system without data augmentation had a sensitivity, specificity, and accuracy of 87.5%, 79.7%, and 83.7%, respectively. While, some data-augmentation techniques decreased diagnostic ability, the ROSE-AI system trained only with the augmented data using the geometric transformation technique had the highest diagnostic accuracy (88.2%). We successfully developed a prototype ROSE-AI system with high diagnostic ability. Each data-augmentation technique may have various compatibilities with AI-mediated diagnostics, and the geometric transformation was the most effective for the ROSE-AI system.

Channel randomisation: Self-supervised representation learning for reliable visual anomaly detection in speciality crops

Modern, automated quality control systems for speciality crops utilise computer vision together with a machine learning paradigm exploiting large datasets for learning efficient crop assessment components. To model anomalous visuals, data augmentation methods are often developed as a simple yet powerful tool for manipulating readily available normal samples. State-of-the-art augmentation methods embed arbitrary “structural” peculiarities in normal images to build a classifier of these artefacts (i.e., pretext task), enabling self-supervised representation learning of visual signals for anomaly detection (i.e., downstream task). In this paper, however, we argue that learning such structure-sensitive representations may be suboptimal for agricultural anomalies (e.g., unhealthy crops) that could be better recognised by a different type of visual element like “colour”.To be specific, we propose Channel Randomisation (CH-Rand)—a novel data augmentation method that forces deep neural networks to learn effective encoding of “colour irregularities” under self-supervision whilst performing a pretext task to discriminate channel-randomised images. Extensive experiments are performed across various types of speciality crops (apples, strawberries, oranges, and bananas) to validate the informativeness of learnt representations in detecting anomalous instances. Our results demonstrate that CH-Rand’s representations are significantly more reliable and robust, outperforming state-of-the-art methods (e.g., CutPaste) that learn structural representations by over 43% in Area Under the Precision–Recall Curve (AUC–PR), particularly for strawberries. Additional experiments suggest that adopting the L∗a∗b∗ colour space and “curriculum” learning in the pretext task — gradually disregarding channel combinations for unrealistic outcomes — further improves downstream-task performance by 16% in AUC–PR. In particular, our experiments employ Riseholme-2021, a novel speciality crop dataset consisting of 3.5K real strawberry images gathered in situ from the real farm, along with the Fresh & Stale public dataset. All our code and datasets are made publicly available online to ensure reproducibility and encourage further research in agricultural technologies.

Novel color vision assessment tool: AIM Color Detection and Discrimination.

Color vision assessment is essential in clinical practice, yet different tests exhibit distinct strengths and limitations. Here we apply a psychophysical paradigm, Angular Indication Measurement (AIM) for color detection and discrimination. AIM is designed to address some of the shortcomings of existing tests, such as prolonged testing time, limited accuracy and sensitivity, and the necessity for clinician oversight. AIM presents adaptively generated charts, each a N×M (here 4×4) grid of stimuli, and participants are instructed to indicate either the orientation of the gap in a cone-isolating Landolt C optotype or the orientation of the edge between two colors in an equiluminant color space. The contrasts or color differences of the stimuli are adaptively selected for each chart based on performance of prior AIM charts. In a group of 23 color-normal and 15 people with color vision deficiency (CVD), we validate AIM color against Hardy-Rand-Rittler (HRR), Farnsworth-Munsell 100 hue test (FM100), and anomaloscope color matching diagnosis and use machine learning techniques to classify the type and severity of CVD. The results show that AIM has classification accuracies comparable to that of the anomaloscope, and while HRR and FM100 are less accurate than AIM and an anomaloscope, HRR is very rapid. We conclude that AIM is a computer-based, self-administered, response-adaptive and rapid tool with high test-retest repeatability that has the potential to be suitable for both clinical and research applications.

CLASSIFICATION OF X-RAY AND CT IMAGES IN DIFFERENT COLOR SPACES USING ROBUST CNN

Since deep learning models have been successfully used in many fields, they have been used to identify sick and healthy people in X-ray or Computed Tomography (CT) chest radiology images. In this study, Covid-19 and pneumonia classification is performed on both X-ray and CT images using the robust Convolutional Neural Network (CNN). BGR, HSV, and CIE LAB color space transformations are applied to X-ray and CT images to show that the model performs a successful classification independent of dataset characteristics. The binary classification accuracy rates of Covid-19 and pneumonia for X-ray images and CT images are 98.7% and 98.4%, 97.6% and 99.4%, respectively. Precision, Recall, Specificity, F1 score, and Mean Squared Error metrics are calculated for each X-ray and CT dataset. In addition, 5-fold cross-validation proved accuracy of the model. Although X-ray and CT chest radiology images are transformed into different color spaces, the proposed model performed a successful classification. Thus, even if the image characteristics of the radiology device brands change, the computer-based system will be able to make successful disease diagnoses at low cost where expert personnel are insufficient.

Leveraging multi-output modelling for CIELAB using colour difference formula towards sustainable textile dyeing

Textile dyeing requires optimizing combinations of ingredients and process parameters to achieve target colour properties. Modelling the complex relationships between these factors and the resulting colour is challenging. In this case, a physics-informed approach for multi-output regression to model CIELAB colour values from dyeing ingredient and process inputs is proposed. Leveraging attention mechanisms and multi-task learning, the model outperforms baseline methods at predicting multiple colour outputs jointly. Specifically, the Transformer model’s attention mechanism captures the complex interactions between dyeing ingredients and process parameters, while the multi-task learning framework exploits the intrinsic correlations among the L*, a*, and b* dimensions of the CIELAB colour space. In addition, the incorporation of physical knowledge through a physics-informed loss function integrates the CMC colour difference formula. This loss function, along with the attention mechanisms, enables the model to learn the nuanced relationships between the dyeing process variables and the final colour output, thereby improving the overall prediction accuracy. This reduces trial-and-error costs and resource waste, contributing to environmental sustainability by minimizing water and energy consumption and chemical emissions.

Combining UAV Multi-Source Remote Sensing Data with CPO-SVR to Estimate Seedling Emergence in Breeding Sunflowers

In order to accurately obtain the seedling emergence rate of breeding sunflower and to assess the quality of sowing as well as the merit of sunflower varieties, a method of extracting the sunflower seedling emergence rate using multi-source remote sensing information from unmanned aerial vehicles is proposed. Visible and multispectral images of sunflower seedlings were acquired using a UAV. The thresholding method was used to segment the excess green image of the visible image into vegetation and non-vegetation, to obtain the center point of the vegetation to generate a buffer, and to mask the visible image to achieve weed removal. The components of color models such as the hue–saturation value (HSV), green-relative color space (YCbCr), cyan-magenta-yellow-black (CMYK), and CIELAB color space (L*A*B) models were compared and analyzed. The A component of the L*A*B model was preferred for the optimization of K-means clustering to segment sunflower seedlings and mulch using the genetic algorithm, and the segmentation accuracy was improved by 4.6% compared with the K-means clustering algorithm. All told, 10 geometric features of sunflower seedlings were extracted using segmented images, and 10 vegetation indices and 48 texture features of sunflower seedlings were calculated based on multispectral images. The Pearson’s correlation coefficient method was used to filter the three types of features, and the geometric feature set, the vegetation index set, the texture feature set, and the preferred feature set were constructed. The construction of a sunflower plant number estimation model using the crested porcupine optimizer–support vector machine is proposed and compared with the sunflower plant number estimation models constructed based on decision tree regression, BP neural network, and support vector machine regression. The results show that the accuracy of the model based on the preferred feature set is higher than that of the other three feature sets, indicating that feature screening can improve the accuracy and stability of models; assessed using the CPO-SVR model, the accuracy of the preferred feature set was the highest, with an R² of 0.94, an RMSE of 5.16, and an MAE of 3.03. Compared to the SVR model, the value of the R2 is improved by 3.3%, the RMSE decreased by 18.3%, and the MAE decreased by 18.1%. The results of the study can be cost-effective, accurate, and reliable in terms of obtaining the seedling emergence rate of sunflower field breeding.

DFUCare: deep learning platform for diabetic foot ulcer detection, analysis, and monitoring.

Diabetic foot ulcers (DFUs) are a severe complication among diabetic patients, often leading to amputation or even death. Early detection of infection and ischemia is essential for improving healing outcomes, but current diagnostic methods are invasive, time-consuming, and costly. There is a need for non-invasive, efficient, and affordable solutions in diabetic foot care. We developed DFUCare, a platform that leverages computer vision and deep learning (DL) algorithms to localize, classify, and analyze DFUs non-invasively. The platform combines CIELAB and YCbCr color space segmentation with a pre-trained YOLOv5s algorithm for wound localization. Additionally, deep-learning models were implemented to classify infection and ischemia in DFUs. The preliminary performance of the platform was tested on wound images acquired using a cell phone. DFUCare achieved an F1-score of 0.80 and a mean Average Precision (mAP) of 0.861 for wound localization. For infection classification, we obtained a binary accuracy of 79.76%, while ischemic classification reached 94.81% on the validation set. The system successfully measured wound size and performed tissue color and textural analysis for a comparative assessment of macroscopic wound features. In clinical testing, DFUCare localized wounds and predicted infected and ischemic with an error rate of less than 10%, underscoring the strong performance of the platform. DFUCare presents an innovative approach to wound care, offering a cost-effective, remote, and convenient healthcare solution. By enabling non-invasive and accurate analysis of wounds using mobile devices, this platform has the potential to revolutionize diabetic foot care and improve clinical outcomes through early detection of infection and ischemia.

The Color Harmony Estimation Model Construction Based on Two Layers of MLE and BPNN in the Color Matching Field

In the field of art, color matching is widely used in various art designs, such as images, posters, clothing, and interior home design. Among them, harmonious color matching is the decisive factor in whether a design is popular or not. To solve the problem of estimating color harmony, this study analyzes from the perspective of color pairs and uses the two-layer maximum likelihood estimation method to make preliminary predictions of color harmony by statistically modeling paired color preferences in existing datasets. After obtaining the preliminary estimation of color harmony, multiple linear regression is selected for denoising processing. Subsequently, the preliminary prediction results were refined using a backpropagation neural network, extracting various color features in different color spaces, and ultimately obtaining accurate harmony estimates. The results indicate that, compared with existing methods, the proposed method can simulate the aesthetic cognition of different users towards different color themes. Under the same statistical method, the model can maintain good harmony estimation and experimental results. This method can promote the development of related research fields, such as quickly evaluating the color harmony of an image, and one click color changing in scenes such as clothing, home, 3D models, etc. according to different user needs.

Multi-color space features and data regression neural network-based method for molten salt temperature detection in rare earth electrolytic processes

To address the online monitoring of molten salt temperature in the rare earth electrolysis process, this paper proposes a rare earth molten salt temperature detection model (MSTDM) based on multi-color space features and data regression neural networks. The model initially preprocesses the collected molten salt temperature images using techniques such as the Gaussian Mixture Model (GMM) and median filtering, followed by color space transformation. Subsequently, 19 hue features used for temperature quantification are extracted, including the channel responses of RGB, HSV, Lab, and Gray color spaces. Finally, a novel data regression neural network (CNN-BiLSTM-Attention) is employed to learn the long-term dependencies between molten salt hue features and temperature, predicting future molten salt temperatures. Experimental results indicate that using the GMM algorithm to filter out flame interference, introducing novel temperature prediction features, and constructing the CNN-BiLSTM-Attention network all enhance the performance of MSTDM in molten salt temperature prediction tasks. The model achieves a mean absolute error of 3.16 °C in predicting molten salt temperatures at rare earth smelting sites. This research not only provides an effective solution for online monitoring of molten salt temperatures in the rare earth electrolysis process but also offers a reliable reference for temperature monitoring in other fields.

Biocompatible sensors for ammonia gas detection

In this work, three different dyes have been tested for the determination of gaseous ammonia. This gas is one of the products of microbial degradation and therefore its presence is an indicator of deterioration and could be used as a food freshness indicator.Three different sensors have been prepared and tested, two of them using the natural pigments curcumin and anthocyanin and the other one using bromothymol blue. All of them are biocompatible and therefore allowed to use in contact with food.Different compositions, materials for deposition, stability and reversibility for ammonia gas detection have been studied under high humidity conditions simulating real packaged food conditions. Colorimetry is the technique used to obtain the analytical parameter, the H coordinate of the HSV colour space, simply using a camera, avoiding the use of complex instrumentation.Sensibility, toxicity grade and stability found show that the sensor could be implemented in packaged food and form the basis of a freshness indicator for the food industry.

Tone mapping algorithm based on BL-Hilbert-L 2 decomposition model for HDR image

Abstract Tone mapping algorithms are mainly used to produce standard dynamic range (SDR) images from high dynamic range (HDR) images. To address the issues of halo artifacts and over-enhancement in current tone mapping algorithms based on layer decomposition model, we propose a tone mapping algorithm based on the BL-Hilbert-L2 decomposition model. In our proposed algorithm, we first convert HDR image from RGB space to HSV space. Subsequently, utilizing the BL-Hilbert-L2 decomposition model, we decompose the V channel of the HDR image into cartoon, texture and high-frequency detail components. Next, we separately compress the cartoon component and stretch the texture and high-frequency detail components. The processed cartoon, texture and high-frequency detail components are then recombined to form a new V channel. Finally, by converting the H and S channels of the HDR image, along with the newly formed V channel, back into the RGB color space, we obtain a tone mapped SDR image. Experimental results demonstrate that our proposed algorithm can effectively eliminate the halo artifacts and avoid the issue of over-enhancement while retaining the edge details.

Potato leaf disease classification using fusion of multiple color spaces with weighted majority voting on deep learning architectures

Potato leaf disease classification using fusion of multiple color spaces with weighted majority voting on deep learning architectures

Phraseological Units with Color Components in the French Language: A Semantic and Cultural Analysis

This article explores the linguistic, semantic, and cultural significance of color-based phraseological units (PUs) in the French language. Colors in French PUs serve as powerful linguistic tools, symbolizing emotions, societal norms, and historical narratives. Through a detailed analysis of common colors such as blue, red, black, and green, this study reveals how these elements function syntactically and convey complex cultural meanings. The challenges of translating French color PUs into other languages are examined, highlighting the difficulties in preserving symbolic meaning and cultural context. This article aims to deepen the understanding of color symbolism in French phraseology and its role in shaping linguistic expression.

Systematic review of Apgar scores & cyanosis in Black, Asian, and ethnic minority infants.

Apgar score and cyanosis assessment may disadvantage darker-skinned babies. This review explored cyanosis and Apgar score assessments in Black, Asian, or minority ethnic neonates compared to White neonates. Four databases were searched. Studies of any methodology were included. A narrative synthesis was undertaken. Ten studies were included. Three studies involving over 39 million neonates showed Apgar score ≤3 was predictive of neonatal mortality across all ethnicities. Black babies with Apgar score ≤3 had lower mortality rates before 28 days, however, variations in scoring practices were also observed. Three further studies (n = 39,290,014) associated low Apgar scores with poorer mental development up to 22 months, especially in mixed ethnicity and Black infants. One study reported inadequate training in assessing ethnic minority neonates. Cyanosis was the focus of three included studies (n = 455) revealing poor visual assessment of cyanosis across ethnicities. With pulse oximetry occult hypoxemia occurred slightly more frequently in Black neonates. Tongue color indicated oxygen requirement at birth, regardless of ethnicity. Apgar scores correlate well with neonatal mortality in all ethnicities, however scoring variations exist. Cyanosis assessment is challenging, with tongue and lips the best places to observe in the absence of pulse oximetry. Assessment of the color component of the Apgar score and of cyanosis visually are not accurate in babies with darker skin. Small racial differences may exist for pulse oximetry in neonates, but it is more reliable than visual assessment.

Realization of narrow-band blue emission based on structurally engineering-designed Bi3+-doped phosphors

The exploration of efficient narrowband emission phosphors is crucial for white light-emitting diodes (WLEDs) in high-performance backlighting applications. Up to now, the discovery of narrow-band Bi3+-doped phosphors for emerging applications remains challenging because Bi3+ typically exhibits broadband emission properties. A novel narrow-band blue phosphor (Ca4SnGe3O12:Bi3+) was successfully synthesized, benefiting from the highly symmetric crystal environment and tightly connected rigid structure of the garnet structure. The phosphor demonstrates broad excitation in the near-ultraviolet (n-UV) region and emits narrowband blue light at 442 nm (FWHM = 36 nm) with a color purity of 94.7 %. In this paper, the assignment of different luminescence centers and the use of Zr/Hf to partially replace Sn to enhance luminescence performance are studied. The reasons for the consequent changes in luminescence behavior are explained in detail. The use of narrowband commercial red K2SiF6:Mn4+, green β-Sialon:Eu2+, and synthetic blue luminescent materials as RGB emitters covered 81 % of the National Television System Committee (NTSC) color space, demonstrating great potential for liquid-crystal-display (LCD) backlight use.

LiPro: displaying concurrent image viewing and imperceptible positioning using visible light

Visible light can be used to achieve effective human interaction with projectors. However, current visible light-based projectors for the target positioning either lose the image viewing function or cause abnormal luminance changes perceived by human eyes, which is not practical for real-world applications. Therefore, we propose a smart lighting-based projector system, LiPro, which can display imperceptible target positioning and any image viewing, simultaneously. In a nutshell, we propose what we believe to be a novel color space conversion modulation scheme to transmit the landmark information, which adds δ and −3δ color intensity value on the red (R) channel and blue (B) channel according to the YCbCr color space analysis, so that human eyes are imperceptible to light intensity changes. Then, we propose the dual-channel decision demodulation scheme, which demodulates the received light signals on both the R channel and B channel at the same time to decide and increase the correctness of the landmark recognition. In the end, we use off-the-shelf devices to implement LiPro to evaluate its performance, and results from extensive experiments show that our LiPro can achieve centimeter-level target positioning under any image viewing conditions.

Exploring the impact of logo colors on the perceived tastes of tea beverages—A study on hand-shaken beverages in Taiwan

Color visually communicates the product’s flavors to consumers and further influences their taste perception. This study explores the perceived taste of tea beverages caused by the logo’s principal colors, using hand-shaken tea beverages in Taiwan as an example. To identify the linkage between the logo color and tea tastes, this study divides the taste of tea beverages into four categories: sweetness, freshness, bitterness, and astringency. Then, the 69 tea beverage logos are allocated into the 14 color sections in the CIELAB color space according to their primary colors. The Correspondence Analysis method is employed to visualize the relationships between the logos and the perceived tastes. The tea tastes are then mapped into the color sections in the CIELAB color space. The analysis results reveal that the sweetness links to logos in the Warm Scheme colors (hue angle from 0 to 59 degrees). The fresh taste is bound with the logo with the Cool White Scheme colors (hue angle from 90 to 149 degrees and brightness >80). Finally, the bitter and astringent tastes link to the logo colors in the Cold Black Scheme colors (hue angle from 60 to 89 degrees, 150 to 329 degrees, and brightness <25). This study expands the color and taste association literature from general food to tea beverages. Our obtained empirical results can be applied to hand-shaken beverage companies to select principal colors for designing logos and packages that align with tea beverages’ perceived tastes to convey brand recognition accurately.

Machine learning with analysis-of-variance-based method for identifying rice varieties

Rice, which has the highest production and consumption rates worldwide, is one of the main nutrients in our country because it is economical and nutritious. Rice undergoes various stages of production from the field to the dinner tables, with the cleaning phase involving separation of rice from unwanted materials. There are different varieties of rice such as arborio, basmati, aracadaga, ipsala, and jasmine. Therefore, it is necessary to identify rice varieties based on customer demands. Rice variety identification is primarily based on its outer appearance, including color, size, and shape. In this study, 75,000 rice grain images, including 15,000 images for each variety, were considered. Using a combination of 12 morphological features, four shape features, and 90 color features obtained from five different color spaces, 106 features were extracted from the images. An analysis of variance (ANOVA) was employed to select high-rank features, which were then fed to a support vector machine (SVM) for classification. The experimental results demonstrated that the utilization of 40 high-rank features yielded impressive outcomes, with a validation accuracy of 99.89 %, cost value of 16, test accuracy of 99.81 %, and cost value of 28. These high accuracy rates are particularly noteworthy, as they indicate the robustness and reliability of the proposed methodology in distinguishing between different rice varieties with minimal error. This high level of precision is critical for practical applications, such as quality control in rice production, to ensure that customers receive the specific rice variety they demand. Implementing this methodology in real-world scenarios could significantly enhance the efficiency and accuracy of the rice variety identification processes, benefiting both producers and consumers.

Color Analysis of Brocade from the 4th to 8th Centuries Driven by Image-Based Matching Network Modeling

To achieve the color matching rules for the textiles discovered during Silk Road excavations between the 4th and 8th centuries, this research proposed an image-based matching network modeling method. The Silk Road facilitated trade and cultural exchange between the East and West, and the textiles found along the way depict the development of fabrics in a color scheme with great cultural significance. A total of 165 images with brocade patterns were collected from a book with a detailed description of the Western influences on textiles along the Silk Road. Two different clustering methods, including the K-means clustering method and octree quantization approach, were used to extract the primary and secondary colors. By combining the HSV color space with the PCCS color system, the color distribution was analyzed to discover the features of representative color patterns. The co-occurrence relationship of the auxiliary colors was explored using the Apriori algorithm, and a total of eight association rules were established. The results showed that the K-means clustering algorithm can show a better effect of color classification to obtain three primary colors and nine secondary colors. The matching mechanism with a visualized network model was also proposed, which showed that reddish-yellow tones are the main colors in the brocade patterns, and the light and soft tones separately account for 27% and 20%. Beige and brown are the most common colorways, with a confidence level of 47%. One style of brocade pattern was used to demonstrate different appearances within various color networks, which could be applied to 3D virtual fitting. This image-based matching network modeling approach makes the color matching schemes visible, and can assist fashion design with fabric features influenced by historical and cultural development.