Color Selection Research Articles

Visible-Light Communication with Lighting: RGB Wavelength Division Multiplexing OLEDs/OPDs Platform.

A multichannel/multicolor visible light communication (VLC) system using entirely organic components, including organic light emitting diodes (OLEDs) and organic photodiodes (OPDs), is developed to demonstrate indoor lighting applications where the integration of OLEDs and OPDs has significant potential. To achieve this, tricolor (Red/Green/Blue(R/G/B))-selective OPD arrays for the receiver and tricolor OLED arrays for the emitter are developed. For (R/G/B)-selective OPDs, a Fabry-Pérot electrode to enhance color selectivity and a thick junction structure to effectively accommodate a wide range of driving voltages are introduced. For tricolor OLEDs, fluorescent-emitting materials are used to enhance the operating frequency in addition to introducing a cavity structure to achieve narrow emission. Utilizing these spectrally refined tricolor OPDs/OLEDs, a VLC system is designed for indoor lighting applications, and a systematic analysis of their signal-to-interference ratio dependence on the distance or angle between the transmitter and receiver is performed. The study's findings indicate the importance of emission angle-dependent wavelength shift of the OLED and the luminosity function, which varies with wavelength, in the R/G/B mixed-white-light-based VLC systems. Finally, the feasibility of VLC using tricolor OPDs/OLEDs in the real-life context of indoor white-color lighting is demonstrated, showing that the transmitted data patterns well-matched the received data patterns.

Analyzing the color availability of AI‐generated posters based on K‐means clustering: 74% orange, 38% cyan, 32% yellow, and 28% blue‐cyan

AbstractIn this exploratory study, we delved deeply into the intricate interplay of color choices within AI‐generated and human‐designed posters, analyzing a sample of 120 instances from each category. While it is suggested that human designers may integrate cultural, emotional, and situational contexts into their creations, AI models largely base their selections on vast datasets and pattern recognition. Although AI exhibited prowess in replicating established design parameters, the study underlined the importance of critically assessing its outputs. The quantitative analysis illuminated overarching similarities in primary color selections. However, the AI's diversity in color remains less concentrated than that of human, suggesting a gap in the AI's capacity to match human expertise in color proportioning and distribution. As AI continues to evolve, it is crucial to discern its capabilities and potential limitations in the design domain, ensuring it augments human creativity rather than supplanting it. Notably, the research refrains from seeking human validation, aiming instead for an objective, data‐driven reflection on the convergences and divergences between AI‐generated and human designs.

Analysis of the Characteristics of the Development of Web-Based Science Learning Media with the STEAM Approach

This research aims to analyze the characteristics of developing Web-Based Science Learning Media using the STEAM approach. This research is development research using the Research and Development (R&D) method with the Thiagarajan 4-D Model which consists of definition, design, development and implementation. Based on the validation results from experts and practitioners, the results are very suitable for use and have character because they have an attractive design, ease of use, and color selection that utilizes color psychology. The features provided are very responsive to learning needs, with an effective project-based STEAM learning flow using scaffolding. Users also have access to Google Data Studio to monitor the progress of each student's STEAM stages and processes. Discussion forums provide flexible interaction and feedback, while STEAM learning modules can be downloaded by teachers for more specific learning situations. The conclusion is that the website developed has unique and unique characteristics that combine color, a project-based STEAM learning flow with a real-time scaffolding system and presents features that make it easier for students to learn

Pengaruh Psikologis Pencahayaan Buatan pada Interior Kamar Tidur Anak

Lighting and color in interior design have a significant influence on the psychology of individuals, especially in children's bedroom spaces. This study aims to identify appropriate lighting colors and understand their effects on children's health and psychology. This research uses qualitative methods of literature study type, by reviewing literature from various sources such as journals, articles, and studies related to lighting, color, and psychology. The research stages include searching for relevant types of literature, reading, reviewing, and presenting the results of literature studies. The results of this study suggest that the color of lighting in children's bedrooms can affect their mood and well-being. Red and yellow colors, when used with low intensity, are suitable for creating a warm and comfortable atmosphere, as well as helping to increase the production of the hormone melatonin, which contributes to better sleep and improves children's mood and mental health. In the context of children's bedroom interior design, the selection of the right lighting colors is essential to create an environment that supports their psychological development and well-being

Assessment of color preference, purchase intention and sexual attractiveness of lipstick colors under multiple lighting conditions.

Lipstick is one of the most commonly used cosmetics, which is closely associated with female attractiveness and influences people's perception and behavior. This study aimed to investigate the impact of light sources, lipstick colors, as well as gender on the subjective assessment of lipstick color products from the prospective of color preference, purchase intention and sexual attractiveness. The correlation between color preference evaluations when applying lipstick on lips and on forearms was also explored. Sixty participants completed their visual assessment of 15 lipsticks worn by 3 models under 5 light sources, with uniformly sampled correlated color temperature (CCT) values ranging from 2,500 K to 6,500 K. The results indicated that the light source significantly influenced color preference and purchase intention, while lipstick color significantly impacted on sexual attractiveness. The interactions between gender and other factors were also observed and are discussed. Compared to men, women were found to be more sensitive to different light sources and hold different attitudes toward different lipstick colors under different CCTs. Interestingly, no significant correlation was found between lipstick color preference ratings on the lips and forearm, which conflicted with the commonly recognized way of lipstick color selection. These findings should contribute to a deeper understanding of the consumer attitude toward lipstick colors and provide a useful reference for lighting design in situations where cosmetics are specified, manufactured, retailed and generally used, both professionally and in the home.

The AGN fraction in high-redshift protocluster candidates selected by Planck and Herschel

ABSTRACT A complete understanding of the mass assembly history of structures in the Universe requires the study of the growth of galaxies and their supermassive black holes (SMBHs) as a function of their local environment over cosmic time. In this context, it is important to quantify the effects that the early stages of galaxy cluster development have on the growth of SMBHs. We used a sample of Herschel/SPIRE sources of ∼ 228 red and compact Planck-selected protocluster (PC) candidates to estimate the active galactic nuclei (AGNs) fraction from a large sample of galaxies within these candidates. We estimate the AGN fraction by using the mid-infrared (mid-IR) photometry provided by the WISE/AllWISE data of ∼650 counterparts at high redshifts. We created an AllWISE mid-IR colour–colour selection using a clustering machine learning algorithm and two WISE colour cuts using the 3.4 $\mu$m (W1), 4.6 $\mu$m (W2), and 12 $\mu$m (W3) passbands, to classify sources as AGN. We also compare the AGN fraction in PCs with that in the field to better understand the influence of the environment on galaxy development. We found an AGN fraction of fAGN = 0.113 ± 0.03 in PC candidates and an AGN fraction of fAGN = 0.095 ± 0.013 in the field. We also selected a subsample of ‘red’ SPIRE subsample with a higher overdensity significance, obtaining fAGN = 0.186 ± 0.044, versus fAGN = 0.037 ± 0.010 of ‘non-red sources’, consistent with higher AGN fractions for denser environments. We conclude that our results point towards a higher AGN fraction in PCs, similar to other studies.

Spectroscopy from Photometry: A Population of Extreme Emission Line Galaxies at 1.7 ≲ z ≲ 6.7 Selected with JWST Medium Band Filters

We use JWST/NIRCam medium band photometry in a single pointing of the Canadian NIRISS Unbiased Cluster Survey to identify 118 extreme emission-line galaxies (EELGs) over 1.7 ≲ z ≲ 6.7, selected using a set of color cuts that target galaxies with extreme [O iii] + Hβ and Hα emission. We show that our medium band color selections are able to select galaxies based on emission-line EW, which is advantageous to more commonly used selections since it does not require strong continuum emission, and can select galaxies with faint or red continuum fluxes. The median EWs of our sample is EW(Hα) = 893 Å and EW ([O III] + Hβ) = 1255 Å and includes some objects with EW ([O III] + Hβ) ∼ 3000 Å. These systems are mostly compact with low stellar mass (median ), low metallicity (median Z = 0.14 Z ⊙), little dust (median A V = 0.18 mag), and high SSFR (median SSFR = 1.18 × 10−8 yr−1). Additionally, galaxies in our sample show increasing EW(Hα) and EW([O iii] + Hβ) with redshift, an anticorrelation of EW(Hα) with stellar mass, and no correlation between EW([O iii] + Hβ) and stellar mass. Finally, we present NIRSpec spectroscopy of 15 of the EELGs in our sample. These spectra confirm the redshifts and EWs of the EELGs calculated from the medium bands, which demonstrates the accuracy and efficiency of our color selections. Overall, we show that there are significant advantages to using medium band photometry to identify and study EELGs at a wide range of redshifts.

The Hoof Color of Australian White Sheep Is Associated with Genetic Variation of the MITF Gene.

Studying the characteristics of mammalian hoof colors is important for genetic improvements in animals. A deeper black hoof color is the standard for breeding purebred Australian White (AUW) sheep and this phenotype could be used as a phenotypic marker of purebred animals. We conducted a genome-wide association study (GWAS) analysis using restriction site associated DNA sequencing (RAD-seq) data from 577 Australian White sheep (black hoof color = 283, grey hoof color = 106, amber hoof color = 186) and performed association analysis utilizing the mixed linear model in EMMAX. The results of GWAS demonstrated that a specific single-nucleotide polymorphism (SNP; g. 33097911G>A) in intron 14 of the microphthalmia-associated transcription factor (MITF) gene was significantly associated with the hoof color in AUW sheep (p = 9.40 × 10-36). The MITF gene plays a key role in the development, differentiation, and functional regulation of melanocytes. Furthermore, the association between this locus and hoof color was validated in a cohort of 212 individuals (black hoof color = 122, grey hoof color = 38, amber hoof color = 52). The results indicated that the hoof color of AUW sheep with GG, AG, and AA genotypes tended to be black, grey, and amber, respectively. This study provided novel insights into hoof color genetics in AUW sheep, enhancing our comprehension of the genetic mechanisms underlying the diverse range of hoof colors. Our results agree with previous studies and provide molecular markers for marker-assisted selection for hoof color in sheep.

Psycho-emotional portrait of primary school-age children with recurrent respiratory infections

Respiratory infections occupy a leading place in the structure of the population’s morbidity, especially among children. At the same time, recurrent respiratory infections (RRIs) impose the main burden on society and families. Most of the factors contributing to the manifestation of the RRI phenomenon have already been well-studied. However, the influence of psychological and emotional aspects on a child’s health has remained largely overlooked. Aim. to study the psychological characteristics of children aged 5–7 years in comparison to episodically ill peers and their correlation with local immunity indicators. Materials and Methods. The study involved 80 children, with 60 in the main group (children with recurrent respiratory infections) and 20 in the control group (episodically ill children). For psychological testing (psychometrics), the following methods were used: Blob Tree test (P. Wilson) to determine motivation and adaptation of children in a group setting. The projective „Family Sociogram‟ test (E.G. Aidemiller) to determine the place of the subject in the system of interpersonal relationships and to assess the nature of communication within the family. A modified version of A. Etkind’s Color Relations Test was used to determine individual typological personality characteristics and attitudes towards significant people and the surrounding environment on both a conscious and partially unconscious level. Clinical laboratory examination included measuring levels of secretory IgA and lysozyme in unstimulated saliva. Results. When analyzing the data obtained, a statistically significant difference was found between the results of children in the main and control groups. Conclusions. During color selection, children with RRIs more often associated themselves with the color red (40.7 %), their mothers with purple (40.7 %), and kindergarten or school with yellow (29.7 %) compared to episodically ill peers (p < 0.05). Children with RRIs in the „Family Sociogram‟ test more often than episodically ill peers demonstrated reduced self-esteem (73 % vs. 30 %, p = 0.038). In the Blob Tree test, children with RRIs differ in their first choice (current position in the group) from episodically ill peers (p < 0.0001). The level of sIgA and lysozyme in saliva in the group of children with RRIs correlates with the sensory choice of color for the mother (p < 0.0001).

Open RT Structures: A Solution for TG-263 Accessibility

BackgroundConsistency of nomenclature within radiation oncology is increasingly important as big data efforts and data sharing become more feasible. Automation of radiation oncology workflows depends on standardized contour nomenclature which enables toxicity and outcomes research, while also reducing medical errors and facilitating quality improvement activities. Recommendations for standardized nomenclature have been published in the American Association of Physicists in Medicine (AAPM) report from Task Group 263. Transitioning to TG-263 requires creation and management of structure template libraries and retraining of staff, which can be a considerable burden on clinical resources. Our aim is to develop a program that allows users to create TG-263 compliant structure templates in English, Spanish, or French to facilitate data sharing. Methods53 pre-made structure templates were arranged by treated organ based on an American Society for Radiation Oncology (ASTRO) consensus paper. Templates were further customized with common target structures, relevant OARs (e.g., Spleen for anatomically relevant sites such as gastroesophageal junction or stomach), sub-site specific templates (e.g. partial breast, whole breast, intact prostate, postoperative prostate, etc.) and brachytherapy templates. An informal consensus on OAR and target coloration was also achieved, though color selections are fully customizable within the program. ResultsThe resulting program is usable on any Windows system and generates template files in practice-specific DICOM or XML formats, extracting standardized structure nomenclature from an online database maintained by members of the TG-263U1 Task Group which ensures continuous access to up-to-date templates. ConclusionsWe have developed a tool to easily create and name DICOM-RT structures sets that are TG-263-compliant for all planning systems utilizing the DICOM standard. The program and source code are publicly available via GitHub, encouraging feedback from community users for improvement and guide further development.

Identification of a novel locus C2 controlling canary yellow flesh color in watermelons.

The flesh color of watermelon is an important trait that is determined by carotenoid composition and affects consumers' fruit desirability. Although a complete dominant control by C locus (Cllcyb) for canary yellow flesh (CY) over red flesh has been reported, red and CY colors frequently appear as a mixed pattern in the same flesh (incomplete canary yellow, ICY) in F1 and inbred lines carrying dominant C alleles. Therefore, we examined the genetic control of the mixed color pattern in ICY using whole-genome resequencing of three ICY (ICY group) and three CY inbred lines (CY group), as well as genetic linkage mapping of an F2 population. The segregation pattern in 135 F2 plants indicated that CY is controlled by a single locus (named C 2) dominant over ICY. The whole-genome resequencing of ICY and CY inbred lines revealed an ICY/CY-specific region of approximately 27.60-27.88Mb on Chr. 2 that was polymorphic between the ICY and CY groups. Our genetic map, using nine cleaved amplified polymorphic sequence markers developed based on the single-nucleotide polymorphisms from the ICY/CY-specific region, confirmed that C 2 is located on Chr. 2 and cosegregated with the marker (M7) derived from a non-synonymous single-nucleotide polymorphism of the pentatricopeptide repeat (PPR) gene (ClPPR, Cla97C02G039880). Additionally, 27 watermelon inbred lines of ICY, CY, and red flesh were evaluated using previously reported Cllcyb (C locus)-based markers and our C 2 locus-linked ClPPR-based marker (M7). As a result, dominant alleles at the C 2 locus were required to produce CY, in addition to dominant alleles at the C locus, while a recessive homozygous genotype at the C locus gave the red flesh irrespective of the genotype at the C 2 locus. Using a ClPPR-based cleaved amplified polymorphic sequence developed in this study and Cllcyb-based markers, watermelon cultivars with CY, ICY, and red flesh could be successfully discerned, implying that the combined use of these markers will be efficient for marker-assisted selection of flesh color in watermelon breeding.

Tanques de armazenamento cilindricos e atmosféricos: otimização de projeto considerando critérios ambientais

Atmospheric tank projects cover a wide range of technical characteristics, ranging from their purpose, according to the regulatory framework, the type of product stored, the technical aspects of the tank to serve this storage with structural safety, and finally, the devices and technical resources to make the equipment financially and economically viable and sustainable. As a basis for criteria for this assessment, the correct regulatory framework for each type of tank, based on its application, and the correct selection of material for its performance and life expectancy, were addressed. Performance improvement criteria were also evaluated, such as the proper sizing of the tank inlet, outlet, and vent nozzles, the use of sensors and devices, and equipment to avoid overpressure or vacuum, and the use of internal floating roofs. In addition, environmental criteria were also presented, such as the correct selection of tank colors and the assessment of their area of ​​incidence of solar radiation. The list of criteria and technical, performance, and environmental details can be further complemented and developed with other characteristics of the tanks, and the objective of this article was to evaluate the main parameters of analysis to guide the developer of the tank project to execute it seeking to optimize technical data with immediate execution and operating costs and the environmental impact of project decisions for welded vertical cylindrical atmospheric storage tanks.

Pengaruh Fashion Influencer Terhadap Warna Busana Generasi Z

Color selection is an important aspect when it comes to purchasing clothes, but there are not many studies linking color in fashion and marketing science. This study analyzes the influencer's attributes on the perceived character of followers so the creation of perceived customer value is established to find purchase intentions, and clothing color preferences in Indonesian’s Generation Z. With a sample size of 388 respondents, the researchers utilized a quantitative descriptive strategy to gather primary data by having survey participants fill out questionnaires. The Structural Equation Model (SEM) approach would then be used to examine the data that was gathered. The results prove that not all variables positively influence purchase intention in clothing color preference and the most desirable clothing colors is pink, blue, and yellow. In order to avoid product waste and improve marketing effectiveness, marketing professionals can use this research as a useful resource when choosing the color of apparel to be produced.
 
 Keywords: fashion color, generation Z, influencer marketing, purchase intention, social media

Community-developed checklists for publishing images and image analyses.

Images document scientific discoveries and are prevalent in modern biomedical research. Microscopy imaging in particular is currently undergoing rapid technological advancements. However, for scientists wishing to publish obtained images and image-analysis results, there are currently no unified guidelines for best practices. Consequently, microscopy images and image data in publications may be unclear or difficult to interpret. Here, we present community-developed checklists for preparing light microscopy images and describing image analyses for publications. These checklists offer authors, readers and publishers key recommendations for image formatting and annotation, color selection, data availability and reporting image-analysis workflows. The goal of our guidelines is to increase the clarity and reproducibility of image figures and thereby to heighten the quality and explanatory power of microscopy data.

Image recognition software geometry with Python and OpenCV

The project aims to develop a software application using Python and various libraries for image processing and manipulation. The software used consists of Windows 10 Pro Education, Python 3.8.2, OpenCV 4.5.3, NumPy 1.22, Imutils 0.5.4, Pillow 9.4.0, Tkinter, and Visual Studio Code 1.75.1. The methodology is divided into four sprints. In the first sprint, the necessary dependencies, including OpenCV, NumPy, Imutils, Pillow, and Tkinter, were installed. The second sprint involved developing a command-line interface and integrating a live webcam video feature. In the third sprint, color detection was implemented by converting the image to black and white and applying filters to identify specific colors. Finally, the fourth sprint focused on developing the selection of geometric figures and colors. When a figure and color were selected, the software would identify and outline the corresponding object. This project utilized Python and various libraries to create an application for image processing and manipulation. The methodology followed a sprint-based approach to gradually develop different features and functionalities of the software.

Chromatics in Urban Landscapes: Integrating Interactive Genetic Algorithms for Sustainable Color Design in Marine Cities

Color design plays a pivotal role in determining whether marine urban landscapes meet the diverse needs of individuals, encompassing their visual, psychological, behavioral, and spiritual dimensions. In the contemporary urban environment, a host of practical challenges, including severe color pollution, the absence of regional cultural characteristics, and a lack of humanistic sensitivity in public spaces’ color schemes, necessitates a thorough exploration of the intricate relationship between color and human psychological needs within environmental contexts. This study leverages the potential of interactive genetic algorithms as a powerful tool for innovative color design solutions. Anchored in the nexus of the environment, human psychology, and color theory, this research delves into the intricate nuances of marine urban landscape color. Employing a comprehensive approach that combines questionnaires and extensive field surveys, we seek to elucidate the critical interplay between color and human well-being. Drawing upon the case study of Zhuhai Shijingshan Park, we harness the principles of interactive genetic algorithms to iteratively design marine urban color patterns. Through this experimentation, our study unveils novel design strategies that harmonize with the psychological idiosyncrasies of the human–environment interface. Specifically, the findings of our research highlight the profound impact of color selection on the emotional and behavioral responses of individuals within marine urban landscapes. Our study contributes vital insights into the art and science of marine urban color design, shedding light on the nuanced ways in which color choices can enhance the quality of urban spaces and promote human well-being. This research endeavors to bridge the gap between marine urban design and human psychology through a comprehensive exploration of color design in marine urban landscapes. By addressing the practical challenges and leveraging innovative design techniques, we strive to provide a holistic understanding of the symbiotic relationship between color and human experience, ultimately enriching the design practices that shape our urban environments.

A striking relationship between dust extinction and radio detection in DESI QSOs: evidence for a dusty blow-out phase in red QSOs

ABSTRACT We present the first eight months of data from our secondary target programme within the ongoing Dark Energy Spectroscopic Instrument (DESI) survey. Our programme uses a mid-infrared and optical colour selection to preferentially target dust-reddened quasi-stellar objects (QSOs) that would have otherwise been missed by the nominal DESI QSO selection. So far, we have obtained optical spectra for 3038 candidates, of which ∼70 per cent of the high-quality objects (those with robust redshifts) are visually confirmed to be Type 1 QSOs, consistent with the expected fraction from the main DESI QSO survey. By fitting a dust-reddened blue QSO composite to the QSO spectra, we find they are well-fitted by a normal QSO with up to AV ∼ 4 mag of line-of-sight dust extinction. Utilizing radio data from the LOFAR Two-metre Sky Survey (LoTSS) DR2, we identify a striking positive relationship between the amount of line-of-sight dust extinction towards a QSO and the radio detection fraction, that is not driven by radio-loud systems, redshift and/or luminosity effects. This demonstrates an intrinsic connection between dust reddening and the production of radio emission in QSOs, whereby the radio emission is most likely due to low-powered jets or winds/outflows causing shocks in a dusty environment. On the basis of this evidence, we suggest that red QSOs may represent a transitional ‘blow-out’ phase in the evolution of QSOs, where winds and outflows evacuate the dust and gas to reveal an unobscured blue QSO.

Feature-based Attentional Amplitude Modulations of the Steady-state Visual Evoked Potentials Reflect Blood Oxygen Level Dependent Changes in Feature-sensitive Visual Areas.

Recent EEG studies have investigated basic principles of feature-based attention by means of frequency-tagged random dot kinematograms in which different colors are simultaneously presented at different temporal frequencies to elicit steady-state visual evoked potentials (SSVEPs). These experiments consistently showed global facilitation of the to-be-attended random dot kinematogram-a basic principle of feature-based attention. SSVEP source estimation suggested that posterior visual cortex from V1 to area hMT+/V5 is broadly activated by frequency-tagged stimuli. What is presently unknown is whether the feature-based attentional facilitation of SSVEPs is a rather unspecific neural response including all visual areas that follow the "on/off," or whether SSVEP feature-based amplitude enhancements are driven by activity in visual areas most sensitive to a specific feature, such as V4v in the case of color. Here, we leverage multimodal SSVEP-fMRI recordings in human participants and a multidimensional feature-based attention paradigm to investigate this question. Attending to shape produced significantly greater SSVEP-BOLD covariation in primary visual cortex compared with color. SSVEP-BOLD covariation during color selection increased along the visual hierarchy, with greatest values in areas V3 and V4. Importantly, in area hMT+/V5, we found no differences between shape and color selection. Results suggest that SSVEP amplitude enhancements in feature-based attention is not an unspecific enhancement of neural activity in all visual areas following the "on/off." These findings open new avenues to investigating neural dynamics of competitive interactions in specific visual areas sensitive to a certain feature in a more economical way and better temporal resolution compared with fMRI.

Text2Color Networks: Deep Learning Models for Color Generation from Compositional Color Descriptions

Color serves as an important cue in graphics, arts and in many computer vision applications. We reliably and effortlessly name colors and communicate them with their names. However, many applications such as graphics, color design, palette generation and color selection tools demand numerical values of colors. Predicting and communicating colors by their numerical values is less intuitive and difficult task as it is a mapping of millions of colors for a specific color space. To bridge the gap between linguistic color names and numerical color values, in this paper, we present neural network architectures that predict a point in color space for a given color name. Proposed models provide user interface between colors and names by learning the language semantics and mimic human level comprehension of color descriptions to predict colors and modify them with respect to linguistic adjectives of color names. We consider color prediction as a regression problem and solve it as a language modeling task. Color descriptions are taken as text sequences and each sentence is represented with word-level tokenization. Each token is transformed into a word vector in the latent space using CBOW word embeddings model. Word vectors representing color names are fed as input to neural networks and trained with normalized R, G, B values as supervision information. Trained models are capable of predicting color for a given color name and modify colors for different nouns and adjectives associated with color names. We also built color generation models based on pre-trained word embeddings to overcome the limited availability of large linguistic color name datasets. These pre-trained models perform well with datasets containing few thousand color names. We then present two recommendation engines that suggest similar color palette to user given color name. These recommendation engines enhance the color vocabulary and assist users in the color selection process.

A Long Skip Connection for Enhanced Color Selectivity in CNN Architectures.

Some recent studies show that filters in convolutional neural networks (CNNs) have low color selectivity in datasets of natural scenes such as Imagenet. CNNs, bio-inspired by the visual cortex, are characterized by their hierarchical learning structure which appears to gradually transform the representation space. Inspired by the direct connection between the LGN and V4, which allows V4 to handle low-level information closer to the trichromatic input in addition to processed information that comes from V2/V3, we propose the addition of a long skip connection (LSC) between the first and last blocks of the feature extraction stage to allow deeper parts of the network to receive information from shallower layers. This type of connection improves classification accuracy by combining simple-visual and complex-abstract features to create more color-selective ones. We have applied this strategy to classic CNN architectures and quantitatively and qualitatively analyzed the improvement in accuracy while focusing on color selectivity. The results show that, in general, skip connections improve accuracy, but LSC improves it even more and enhances the color selectivity of the original CNN architectures. As a side result, we propose a new color representation procedure for organizing and filtering feature maps, making their visualization more manageable for qualitative color selectivity analysis.