Research note: Comparative estimation of genetic parameters for eggshell pigmentation traits.

Carnation (Dianthus caryophyllus) contains abundant flavonoid glycosides (FGs), which are important natural functional and colour components. However, there are few reports on the modification of UDP-glycosyltransferases (UGTs) in relation to flavonoids in carnation. In this study, we cloned and characterised a flavonoid 3'-O-glucosyltransferase (UGT73A93) in carnation invitro. Overexpression of UGT73A93 in carnation and tobacco increased flavonoid glycoside accumulation, particularly kaempferol glycosides, while decreasing anthocyanin content and lightening flower colour. UGT73A93 also enhanced fungal resistance, antioxidant capacity, anti-amylase and anti-pancreatic lipase activities. Yeast one-hybrid and dual-luciferase assays revealed that the UGT73A93 promoter interacted with DcH3.3 and DcNAC1, key regulatory proteins involved in flavonoid biosynthesis. We predicted the interaction between DcLON2 and DcNAC1 using AlphaFold 3 and confirmed this hypothesis through yeast two-hybrid assay and bimolecular fluorescence complementation assays. These findings suggest an epigenetic-transcriptional cascade (DcH3.3-DcNAC1-UGT73A93) wherein DcH3.3 opens chromatin for DcNAC1-mediated UGT73A93 activation, while DcLON2 potentially degrades DcNAC1 to form a feedback loop. These results provide new insights into flavonoid 3'-O-glucosyltransferase and may contribute to future strategies aimed at improving the benefits of flavonoid biosynthesis for both plants and humans. It also demonstrates that AI can be applied in the field of plant biosynthesis, accelerating the process of plant breeding.

Projection mapping (PM) optically overlays computer-generated imagery onto real-world objects, enabling users to experience augmented reality without wearing any display devices. However, surface textures often cause color distortion, leading the displayed colors to deviate from the desired colors. To address this issue, we propose a projector radiometric compensation method that minimizes the color difference between a target image and the projected result using a 2D spectroradiometer (2DSR). In the proposed method, we model the color transformation between the projector and the 2DSR in a differentiable manner. Based on this formulation, we propose two optimization strategies for projector radiometric compensation: (i) minimizing the spectral error between the target appearance and the projected result, and (ii) minimizing the color difference measured in a differentiable color space designed to reflect human visual perception. Experiments with a physical prototype demonstrate that our method achieves more accurate projector radiometric compensation and better alignment with human color perception than conventional methods using an RGB camera.

In this paper, we propose and develop a novel variational model based on hue-saturation similarity and fuzzy membership function for color image segmentation. The main contribution of the proposed model is that we determine different segments by using the similarity of hue and saturation information in hue, saturation, and value color space. We first provide specific definitions of the hue/saturation distance to describe hue-saturation similarity, then formulate a novel data fitting term with an adaptive weight coefficient by using hue-saturation similarity in the proposed energy functional. Two efficient iterative algorithms based on coordinate descent method and alternating direction method of multipliers have been proposed to solve the proposed optimization problem. Theoretically we study the existence of the solution of the proposed model and the convergence of the proposed coordinate descent algorithm. Numerical experimental results demonstrate that the segmentation performance of the proposed model is much better than that of other existing color image segmentation methods.

Modern video compression is implemented in complex software systems that reuse software modules from various sources. This is particularly evident in experimental software systems designed for researching and standardizing new compression technologies. These systems often incorporate software modules operating in different color spaces. For example, AI-based techniques are often used in video coding experiments. The corresponding software modules often operate on RGB representations, while other modules operate on YCBCR components. In this study, we demonstrate that the quality loss resulting from color transformations is comparable to the respective quantization noise. Consecutive cycles of color transformations do not result in significant additional degradation. However, for image compression, very different results are obtained in different color representations. This aspect must be carefully considered in compression research. This paper supports these considerations with extensive experimental results in the context of ITU Recommendations BT.709 and BT.2020, as well as AVC and HEVC compression.

We propose a Dual-Channel assisted Music Emotion Perception and Visualization (DC-MEPV) framework designed for ambient lighting in intelligent vehicle cockpits, addressing the increasing demand for advanced human–machine interaction in the automotive industry. This framework consists of three main components: the Multi-Scale Feature Extraction Block (MSFEB), the Global Sequence Modeling Block (GSMB), and the Emotional Color Visualization Algorithm (ECV-Algo). The MSFEB extracts valence and arousal (V-A) features from dual channels at multiple temporal scales, with each channel employing a hybrid neural network architecture to capture multi-scale emotional representations. The GSMB integrates positional encoding, bidirectional long short-term memory (BiLSTM) networks, and multi-head self-attention mechanisms to dynamically model global emotional sequences. The ECV algorithm utilizes personalized emotion–color association rules to achieve expressive emotion-driven lighting visualization based on a continuous mapping from emotion space to color space. We conducted comprehensive comparison and ablation experiments to evaluate the model’s emotion perception performance, and designed three metrics to evaluate the quality of the generated visualizations. The model outperformed other networks in both comparative and ablation experiments. Additionally, the generated lights demonstrated strong performance in terms of CIEDE2000 variation rates, unique color ratios, and joint histogram entropy. DC-MEPV achieved excellent performance in emotion perception and visualizations on the DEAM and PMEmo datasets.

Content-Based Image Retrieval (CBIR) systems critically depend on discriminative yet efficient feature representations to retrieve relevant images from large-scale databases. However, many existing handcrafted and graph-based methods face limitations in scalability and in jointly modeling multimodal information such as color, texture, and spatial relationships. To address these challenges, this paper proposes a novel feature extraction framework termed Multi-modal Graph Color SIFT (MGC-SIFT). In the proposed approach, color-augmented SIFT descriptors extracted in the YCbCr color space are organized as a graph of local keypoints, over which Graph Neural Networks (GNNs) are applied to model inter-keypoint spatial relationships. An attention mechanism is incorporated to emphasize discriminative keypoint regions, while proxy-based learning is employed to improve representation compactness and retrieval efficiency.The effectiveness of MGC-SIFT is evaluated on four benchmark datasets—Corel-1K, COIL-20, Oxford-102 Flowers, and UC-Merced Land Use—covering natural scenes, controlled object images, fine-grained categories, and aerial imagery. Experimental evaluation using standard CBIR metrics, including mean Average Precision (mAP), Precision@k, Recall@k, F1-score@k, and Accuracy@k, demonstrates that the proposed method achieves consistent and competitive retrieval performance across heterogeneous datasets, including robustness under image degradation conditions. Ablation studies further confirm the complementary contributions of color augmentation, graph-based modeling, attention mechanisms, and proxy-based learning. In addition, runtime and memory analysis indicate that proxy-based learning significantly reduces retrieval latency, supporting scalable image retrieval.Overall, the proposed MGC-SIFT framework provides a robust and interpretable multimodal representation for CBIR by explicitly modeling joint color–spatial dependencies at the local keypoint level, offering a practical solution for scalable image retrieval in real-world applications.

Information security is critically important. We propose a multilevel electrochromic display design for dynamic information encryption, enabled by Prussian blue, zinc, and potassium nickel hexacyanoferrate. The as-fabricated electrochromic devices offer a two-dimensional CIE color space modulation with four distinct states from transparent to blue, green, and yellow. The devices facilitate precise, localized, and dynamic modulation of electrochromism via an elaborately designed and independently addressable pattern configuration, enabling advanced encryption and identity authentication with enhanced adaptability. This approach achieves superior security through multi-stage authentication, real-time color modulation, and adjustable smart encryption levels tailored to different specific requirements. Our work envisions a new generation of flexible electrochromic devices that elevate both display performance and information security.

ABSTRACT Information security is critically important. We propose a multilevel electrochromic display design for dynamic information encryption, enabled by Prussian blue, zinc, and potassium nickel hexacyanoferrate. The as‐fabricated electrochromic devices offer a two‐dimensional CIE color space modulation with four distinct states from transparent to blue, green, and yellow. The devices facilitate precise, localized, and dynamic modulation of electrochromism via an elaborately designed and independently addressable pattern configuration, enabling advanced encryption and identity authentication with enhanced adaptability. This approach achieves superior security through multi‐stage authentication, real‐time color modulation, and adjustable smart encryption levels tailored to different specific requirements. Our work envisions a new generation of flexible electrochromic devices that elevate both display performance and information security.

Optimizing images of normal and diseased potato leaves in RGB color space with squeezenet and harris hawk algorithms and determination by SVM

In healthy wood, color variations can betray structural changes that substantially affect the quality of the raw material. In the case of silver fir (Abies alba), compression wood is a very common structural anomaly. The material used for this study originates from centenary trees and serves to verify how the color of the wood responds to structural changes caused by the formation of compression wood. The color changes were tracked in the CIELab color space for different types of wood structures, such as normal wood, mild, moderate and severe compression wood. They occur in all directions of the wood, under the influence of compression stress and the cambium age, and they are discussed in relation to fluctuations in chemical composition at the tree level. Results of this study revealed that the color redness and yellowness react promptly to structural changes, and reveal the intensity levels of compression wood (mild, moderate, and severe). It was noticed that lightness is slightly sensitive to the onset of compression wood. Clear trends in wood color change along the trees were observed. The chromatic specificity of compression wood and its relationship with the environment could allow historical reconstruction and monitoring of tree life conditions through wood color.

Color harmony is a form of visual aesthetics that exists in digital art and influences the perception, emotion and the quality of the entire design. The more complex the digital creation of art, the more the systematic means of picking out combinations of colors is becoming a necessity as a replacement of the older systems of color combinations that were picked out intuitively. The authors have discussed in this paper the computational colour theory model in visual harmony optimisation in the creation of digital artwork by integrating conventional colour theories with the latest algorithmic and data-driven techniques. The paper explains the theory of colour and colour space perceptions, and the measures of harmony, and then goes further to explain the computational methods of rule-based systems, mathematical modelling, optimization algorithms and machine learning strategies. It is recommended to introduce a comprehensive implementation structure, such as system architecture, data preparation, model training and digital art pipeline preparation. Experimental evaluation based on quantitative measurement is achieved using quantitative measures, such as perceptual color distance, harmony scoring and contrast ratio, and mean squared error and qualitative user study. The results show that machine learning and hybrid networks are more effective in the accuracy and aesthetic quality to provide more flexible and context-sensitive color suggestions. Subjectivity of color perception, biased datasets, and the complexity of computations involved is a critical concern (which will be discussed in the paper) and future prospects, including the use of individualized color models, interpretable AI, and real-time optimization systems are mentioned.

The classification of tomato ripeness is crucial for post-harvest processing, quality assurance, and agricultural automation, as manual evaluation is often subjective, inconsistent, and time-consuming. This research investigated the impact of color space selection and hyperparameter optimization on tomato ripeness classification using machine learning (SVM, Random Forest, K-NN, GNB) and deep learning (CNN) approaches. Evaluation results indicated that YCbCr was the best-performing color space for classical models, with SVM achieving the highest accuracy (91.24%) and RF following closely (89.54%), whereas HSV yielded optimal performance for CNN (90.46%), highlighting differences in feature extraction mechanisms. Confusion matrix and ROC curve analyses demonstrated that models capturing nonlinear and interdependent color features, such as SVMs and CNNs, achieved superior class separability, particularly for the Ripe and Unripe classes. Dominant channel analysis revealed that chrominance channels, Cb in YCbCr and H in HSV, played a critical role in ripeness discrimination. These findings emphasized the importance of preprocessing for feature selection and provided guidance on selecting appropriate models and color spaces to improve the accuracy and reliability of automated tomato ripeness classification.

ABSTRACT Image denoising is a fundamental task in computer vision aimed at restoring clean images from noisy inputs. Conventional methods often struggle with synthetic images due to the sensitivity of the human visual system to such noise. This paper proposes a novel Colour Component Decomposition Denoising Network (CCDDNet) for blind Gaussian image denoising, where noise levels are unknown during testing. The approach decomposes images into bit planes and denoises RGB components separately using dedicated convolutional neural networks with multi-layer residual learning. This progressive strategy effectively removes noise while preserving fine details and overall image quality. Experimental results on benchmark datasets, including BSD100, Kodak24, and Urban100, demonstrate superior performance, achieving up to 37.78 dB PSNR and 0.978 SSIM, outperforming state-of-the-art methods such as Restormer and KBNet. These results confirm the effectiveness and robustness of CCDDNet across varying noise levels and diverse image conditions.

Abstract A genome‐wide association study (GWAS) using digital images was conducted to delineate regions of the genome that govern the leaf flipping quantitative trait in soybean ( Glycine max (L.) Merr). However, converting the digital data to numerical scores for downstream analyses was challenging. We have developed an algorithm that operates in the hue, saturation, and value color space in a structured image processing pipeline that includes preprocessing, binary masking for leaf region isolation, contrast enhancement, grid‐based intensity analysis, and thresholding for detecting folded leaves, a response of soybean to drought. The outputs of this image analysis reached over 90% detection accuracy for images captured under different imaging conditions. GWAS using the processed images identified the same genetic loci underlying drought tolerance as were identified earlier by GWAS of the manually curated dataset from the same photos. This approach provides a robust, scalable, and cost‐effective tool for digital image‐based high‐throughput phenotyping.

Hue percepts vary more rapidly along some directions in color space (e.g., near yellow) than others (e.g., near green), with corresponding differences in the size or stimulus range of different hue categories. The basis for these differences is not known. We examined whether the asymmetries are present in early cortical color coding by comparing the strength of hue differences using visual evoked potentials (VEPs) recorded from the occipital cortex. Stimuli were spatial gratings with a fixed nominal contrast in the cone-opponent plane that varied sinusoidally in hue rather than saturation. The responses to different levels of hue separation were measured by the amplitude of the frequency-tagged signals and also in behavioral measurements employing a contrast matching task. For both, the same separation in hue angle resulted in stronger responses for angular differences centered on the yellow quadrant of the cone-opponent space. Responses were also larger for the yellow than blue quadrant, ruling out a general sensitivity loss to the blue-yellow axis as the basis for the differences. The response differences paralleled the asymmetries in the rates of change in color appearance based on analyses of previous measures of hue scaling functions. The presence of these asymmetries in the VEP responses suggests that they arise relatively early in the cortical sensory representation of color rather than emerging late as a product of inference or color category learning.

To address the low accuracy of traditional freshness detection/grading and poor adaptability to different shell colors in the duck egg industry, this study developed a non-destructive detection model and an integrated device for duck egg freshness based on machine vision combined with eggshell optical property analysis. A four-sided yolk transmission imaging system was designed, and accurate yolk region segmentation was achieved via grayscale conversion, a weighted improved Otsu algorithm for whole-egg segmentation, histogram equalization enhancement, and K-means clustering in the LAB color space. A relational model between the average four-angle yolk projected area ratio and Haugh Units (HU) freshness grades was constructed, with grading thresholds determined by constrained optimization combined with the Youden index to balance food safety and grading accuracy. Experimental results showed the model achieved an overall freshness grade discrimination accuracy of 91.3%, with a sensitivity of 97.1% and specificity of 98.9% for inedible Grade B (HU < 60) duck eggs and below. An automated testing device was further developed, adopting a roller-rotating motor collaborative mechanism for automatic flipping and imaging, and equipped with a 10 W/5500 K LED cool white light source to solve the problem of poor adaptability to different shell colors. The device achieved an overall discrimination accuracy of 88.5% with a detection time of ≤5 s per egg, and its host computer can real-time output the yolk area ratio, predicted HU value, and freshness level. This study provides a high-precision and low-cost technical solution for the refined grading of the poultry egg industry.

Color perception entails multiple processing levels. Perceptual dynamics in color vision and the role of stimulus history can be studied using the phenomenon of hysteresis, well-known in the framework of physical dynamical systems. In perceptual hysteresis paradigms, stimuli change gradually, leading to competition between perceptual stabilization (positive hysteresis) or early change to an alternative percept (negative hysteresis). The former dominates in most perceptual domains, such as motion, letter or emotion recognition. The question remains whether positive hysteresis dominates in color perception like in most other perceptual domains where positive lags dominate. If instead negative hysteresis occurs, color perception changes should occur earlier than expected and be manifested as a negative lag. Adaptation is a possible mechanism underlying negative hysteresis, because it favors earlier perceptual switches. In our study investigating the role of stimulus history, we studied hysteresis in color perception under different conditions using a dynamic color-matching task within Derrington-Krauskopf-Lennie (DKL) color space. Color matching experiments under hysteresis conditions can be used to determine hysteresis lags (negative color matching lag to a reference stimulus implying negative hysteresis). Our color-matching tasks, under manipulation of temporal context, using classical experimental hysteresis approaches, required either comparison of single-color shapes or complex multi-part objects (one serving as the reference and the other as the time varying target) composed by multiple elements and requiring holistic perceptual binding. These color matching tasks were undertaken under conditions of direct visual stimulus presentation or under visual memory guidance (reference only present in short term memory) (N=20, healthy participants). We specifically examined these processes along two axes: the S-(L+M) and L-M axes in DKL color space. We found that negative hysteresis dominates in color processing . We found that negative hysteresis predominates in simple color-matching tasks (t=-5,81, df 19, p<0.001, Cohen's d=2,8), even in the physical absence of the reference, when visual memory is required in contrast with tasks requiring binding (F=28.1, df=3, p<0.001, eta-square=0.596). This suggests that adaptation, indexed by negative hysteresis, prevails over visual persistence, indexed by positive hysteresis, in color-matching of simple objects. By using more complex holistic color-matching we further asked if perceptual binding is affected by hysteresis. However, negative hysteresis is absent when holistic perceptual binding is necessary, indicating that these processes occur at distinct hierarchical stages of visual processing. This study marks the first exploration of hysteresis in color perception. In sum, negative hysteresis dominates in early color processing (likely at V1 and V2 levels), while holistic perceptual binding and matching of multiple color elements occurs independently of hysteresis, at a subsequent attentive processing stage.

Study on quality evaluation of the entire stir-frying process of charred stir-fried malt based on intelligent sensing and machine learning.

Image segmentation and registration of carp brain tissue slices oriented to brain atlas construction.