Illumination Color Research Articles

An efficient implementation of traffic signs recognition system using CNN

In the modern world, road traffic signs are vital for drivers safety. In fact, multistep traffic forecasting on road networks can help to avoid many problems on the streets. In this context, there are several methods which allow to achieve excellent results in the field of traffic signs recognition. Recently, Deep Convolutional Neural Network (CNN) have achieved excellent results in this area.In this paper, CNN is used to develop a Traffic and Road Sign recognition system. The performance of the proposed architecture is measured using a novel dataset, namely the Tunisian traffic signs dataset. In addition, we minimize the number of layers in the LeNet network, lowering the number of parameters in the network to accelerate the computation. Our architecture was used with varying parameters in order to achieve the best recognition rates in uncontrolled environment including weather conditions, complex background, variable illumination, and sign color fading. The Experimental results show that the proposed CNN architecture achieved a significant accuracy, thus higher than those achieved in similar previous studies.

Topographical aspects of brief-stimulus presentations: A re-examination of the problem of conditioned reinforcement

Three pigeons were exposed to second-order schedules in which responding under a fixed-interval (FI) component schedule was reinforced according to a variable-interval (VI) schedule of food reinforcement. Completion of each component resulted in either (1) brief presentation of a stimulus present during reinforcement (paired brief stimulus), (2) brief presentation of a stimulus not present during reinforcement (nonpaired brief stimulus), or (3) no stimulus presentation (tandem schedule). Under the two nonpaired brief stimulus conditions, either a change in keylight color or onset of houselight illumination was used as the brief stimulus. Similar patterns of keypecking occurred under tandem and nonpaired keylight brief-stimulus presentations, whereas nonpaired houselight brief-stimulus presentations generated positively accelerated within-component keypeck patterning for two pigeons. When the same keylight brief stimulus was paired with food, positively accelerated patterns of keypecking were obtained for all pigeons. Differences in the effects of nonpaired brief-stimulus presentations on second-order schedule performance suggest that component schedule patterning under nonpaired brief-stimulus procedures is a function of the particular type of stimulus used (i.e., houselight versus keylight). These results suggest that (1) brief houselight illumination may function as a sensory reinforcer, and (2) a briefly presented food-paired stimulus can function as an effective conditioned reinforcer.

An Automatic Jujube Fruit Detection and Ripeness Inspection Method in the Natural Environment

The ripeness phases of jujube fruits are one factor mitigating against fruit detection, in addition to uneven environmental conditions such as illumination variation, leaf occlusion, overlapping fruits, colors or brightness, similar plant appearance to the background, and so on. Therefore, a method called YOLO-Jujube was proposed to solve these problems. With the incorporation of the networks of Stem, RCC, Maxpool, CBS, SPPF, C3, PANet, and CIoU loss, YOLO-Jujube was able to detect jujube fruit automatically for ripeness inspection. Having recorded params of 5.2 m, GFLOPs of 11.7, AP of 88.8%, and a speed of 245 fps for detection performance, including the sorting and counting process combined, YOLO-Jujube outperformed the network of YOLOv3-tiny, YOLOv4-tiny, YOLOv5s, and YOLOv7-tiny. YOLO-Jujube is robust and applicable to meet the goal of a computer vision-based understanding of images and videos.

Optical and Color Properties of Gamma Irradiated Polyvinyl Alcohol - Sodium lignosulfonate-Cadmium sulfide Nanocomposite Films

We prepared a nanocomposite (NC) film containing sodium lignosulfonate (LS), polyvinyl alcohol (PVA) and nano-sized cadmium sulfide (CdS) using the thermolysis and ex-situ casting procedures. Samples from the prepared PVA-LS/CdS NC film were exposed to gamma radiation doses (2 − 20 kGy). To study the resultant outcome of the gamma ray irradiation on the optical and color properties of the synthesized NCs, we used UV-vis spectroscopy and the International Commission on Illumination (CIE) color changes technique. When the gamma dose was increased to 20 kGy, the refractive index increased along with a decrease in the direct optical bandgap from 4.41 to 3.90 eV. We attribute this to the dominance of crosslinking that damaged the ordered configuration and thus increased the amorphous phase. This suggests that the gamma radiation can facilitate the spreading of CdS within the composite matrix suggesting an extra compacted structure of the PVA-LS/CdS NC samples. Moreover, the values of Eg, obtained from ε″ vs. energy plots were close to those values obtained by means of Tauc’s relation, indicating that the NC films exhibited a direct allowed transition. Finally, the color changes between the pristine and irradiated samples were characterized. The pristine PVA-LS/CdS NC film exhibited substantial color differences.

Color Classification Under Complex Background via Genetic Algorithm-Based Color Difference Histogram

Color classification of polycrystalline silicon solar cells is really challenging for performing the task of production quality control during the manufacturing due to the non-Gaussian color distribution and random texture background. The motivation of this work is to present a robust color classification technique by designing a novel tiny color difference feature descriptor. Thus, a genetic algorithm based color difference histograms (GACDH) is proposed. First, the optimal color space of color difference histogram (CDH) to represent tiny color changes is designed. It counts the perceptually uniform color difference in a small local neighborhood in the L*a*b* color space, which reduces the false classification due to small color variations and illumination variation. Second, the genetic algorithm based color quantization for CDH is proposed to select the optimal quantization bins in the L* component, then we make some comparative experiments in a* and b* color components to select optimal quantization bins. The optimization of feature dimension not only reduces the large dimensionality of histogram bins in the computation but also improves the following classification performance. Finally, the proposed algorithm is validated with color dataset of solar cells with distance measure method. Some experimental results and analysis show that the overall performance of the proposed method achieves 98.6% and outperforms other techniques available in the literature in terms of weak discriminative color difference classification.

Computer vision analysis of sample colors versus quadruple-disk iridium-platinum voltammetric e-tongue for recognition of natural honey adulteration

This work presents a deep learning approach for computer vision-based recognition of natural honey adulteration. The results are compared with the machine learning models using chemical data obtained with an innovative bimetallic voltammetric electrode that acts as an e-tongue. Computer vision is based on the recognition of the color of the sample, which changes with the addition of undesirable synthetic substances. The pictures were taken with a smartphone under controlled conditions using seven different background illumination colors for samples that contained 0 – 50 % foreign additives. In the best case root mean square error (RMSE) in the regression approach was 0.46 % for the external test set at R2 = 0.9993, calculated as a compatibility evaluation between the true values and the prediction result. The minimum RMSE for the voltammetric measurements on the quadruple-disk iridium-platinum electrode and the regression algorithms PCR, PLSR, and SVR was 0.25 % with R2 = 0.9998. It has been shown that when food adulteration affects its color, it is possible to successfully replace the classical e-tongue with computer vision. The convenient, rapid, and nondestructive approach does not require the use of equipment, reagents, or solvents and laboratory work techniques typical for analytical chemistry.

Hybrid model of alternating least squares and root polynomial technique for color correction

Color correction is an image-altering technique that modifies image color in such a way that it matches a reference image. Many approaches have already been proposed by various researchers; however, those models have been unable to reduce color errors between two images, which results in inefficiency and poor-quality images. This research paper presents an effective and improved color correction model wherein alternate least square (ALS) and root polynomial (RP) are used together. The main objective of the proposed model is to reduce the error between a reference image and a target image to enhance the image quality and make them look realistic. To achieve this objective, the proposed model used the Amsterdam library of object images which contains a picture of single objects captured under various illumination angles and colors. The main contribution of this paper is a hybrid ALS + RP color correction technique, implemented on the dataset image that fixes its color as per the reference image and enhances its quality. The target image is then converted into three color models, i.e., LAB, LUV, and RGB into XYZ format. Finally, the color difference between a reference image and a target image is observed by calculating values for parameters like Mean, median, 95% quantile, and maximum error. The effectiveness of the suggested hybrid color correction approach is assessed and validated in MATLAB software for each color model. Through extensive experiments, it is observed that the proposed hybrid model yields the least errors for the RGB color model. This is followed up by LUV and then LAB, to prove its supremacy over other models.

Weakly and semi-supervised detection, segmentation and tracking of table grapes with limited and noisy data

Detection, segmentation and tracking of fruits and vegetables are three fundamental tasks for precision agriculture, enabling robotic harvesting and yield estimation applications. However, modern algorithms are data hungry and it is not always possible to gather enough data to apply the best performing supervised approaches. Since data collection is an expensive and cumbersome task, the enabling technologies for using computer vision in agriculture are often out of reach for small businesses. Following previous work in this context (Ciarfuglia et al., 2022), where we proposed an initial weakly supervised solution to reduce the data needed to get state-of-the-art detection and segmentation in precision agriculture applications, here we improve that system and explore the problem of tracking fruits in orchards. We present the case of vineyards of table grapes in southern Lazio (Italy) since grapes are a difficult fruit to segment due to occlusion, colour and general illumination conditions. We consider the case in which there is some initial labelled data that could work as source data (e.g. wine grape data), but it is considerably different from the target data (e.g. table grape data). To improve detection and segmentation on the target data, we propose to train the segmentation algorithm with a weak bounding box label, while for tracking we leverage 3D Structure from Motion algorithms to generate new labels from already labelled samples. Finally, the two systems are combined in a full semi-supervised approach. Comparisons with state-of-the-art supervised solutions show how our methods are able to train new models that achieve high performances with few labelled images and with very simple labelling.

Increasing Consumer Drone Safety Through an IoT-Based Custom Illumination System

Consumer-based drone applications have been increasing rapidly in recent years. Most of these applications, such as aerial surveillance, crop dusting, and real estate photography rely, on frameworks that are based on the Internet of Things (IoT). Although solutions have been proposed to security issues due to connectivity, physical safety issues have not been sufficiently discussed. To solve one such issue, the conspicuousness of drones during flight, we have proposed an illumination system that can adapt to different weather conditions using an IoT framework. To test the feasibility of our illumination system, we conducted two tests, a power consumption test, and a human-in-the-loop assessment. The power test showed different illumination configurations did affect power consumption. The human-in-the-loop assessment demonstrated the effect of illumination on distance perception and how sunlight levels affected the drone's preferred illumination color. As drones begin to operate in more crowded spaces, such as cities, the need to ensure the safety of the public will be paramount. Through this prototype, we aim to provide designers with guidance on how to consider illumination for safer drone operations. Future studies, we plan to explore using illumination to increase safety and congruence in future application areas, such as delivery.

VR 환경 속에서 색온도 및 조도(照度)가 환경인지도와 길찾기에 미치는 영향

The purpose of this study is to investigate the influence of color temperature and lx conditions on human pathfinding and environmental perception in virtual environment.In addition, in CG virtual reality environment, how to use color temperature, light color and light flux variables to solve and improve the cognitive and pathfinding ability of virtual environment is studied.The data of participants (N=60) in virtual reality environment with various light and color conditions were investigated, and the differences were evaluated using SD psychological survey method.The results show that low color temperature (warm color) has higher attraction and memory score than high color temperature and neutral color temperature.Furthermore, the study confirmed that the use of color temperature in a virtual environment with low-throughput light levels, regardless of color temperature, results in negative effects.Therefore, low color temperature (warm color) lighting environment can be used as an effective wayfinding landmark, but wider use of high color temperature (cold color) lighting conditions are considered to be more conducive to pathfinding and traffic efficiency.In addition, the results show that women prefer high-brightness virtual environments to men.

Reasonable use of Indoor Lighting in Human Living Environment

In today's life, lighting design has become a very important part of the indoor environment, affecting not only the presentation of the design, but also human health. In current lighting designs, there is still a lack of attention to the use of lighting, resulting in visual and health discomfort for occupants. Based on the original light research, this paper analyzes and applies the light to explore the most scientific direction of light use. Analysis of color temperature, light flux, illumination, and other data of lighting types on the market, and investigation of the effect on human perception. The types of lighting should also not be harmful to the eye and safe to use for long periods of time. Reflective materials are another alternative method to reflect natural lighting to the room to bring spaciousness when there is no available natural lighting directly. In the future, there should be experimental lighting that may mimic or replace lighting in nature, or lighting that is fully adapted to the user's senses, emotions, and fatigue. This paper looks forward to finding more appropriate ways to use interior lighting and is dedicated to addressing unreasonable lighting designs in interior design.

An integrated method for color correction based on color constancy for early mural images in Mogao Grottoes.

Restoring the correct or realistic color of a cultural heritage object is a crucial problem for imaging techniques. Digital images often have undesired color casts due to adverse effects caused by unstable illuminant conditions, vignetting, and color changes due to camera settings. In this work, we present an improved color correction method for color cast images that makes the color appear more realistic. It is based on a computational model of the human visual system that perceives objects by color constancy theory; it realizes illumination non-uniformity compensation and chromaticity correction for color cast images by taking into account the color stability of some pigments. This approach has been used to correct the color in Cave 465 of the Mogao Grottoes. The experimental results demonstrate that the proposed method is able to "adaptively correct" color cast images with widely varying lighting conditions and improve the consistency efficaciously. It can achieve improved consistency in the mean CIEDE2000 color difference compared with the images before correction. This colorimetric correction methodology is sufficiently accurate in color correction implementation for cast images of murals captured in the early years.

Transition type influences the adaptation state under dichromatic illuminations.

The CATs models proposed over these years (such as CMCCAT97, CAT02 and CAT16) were derived from simple stimuli surrounded by a uniform background with a single illuminant. However, the real scene always consists of more than one illumination, especially in many artificially lit environments. Some previous studies indicate an influence of the transition type between two illuminations on the adaptation state, but the visual data is insufficient to conclude a general trend applicable for any color pair. To systematically investigate how the transition type and illumination color pair interactively influence the adapted white point and degree of adaptation, a series of achromatic matching experiments were conducted under (simultaneously) spatially dichromatic illuminations. Transition type was found to have an impact on the adaptation state, but it is significant only for an illumination pair with a large color difference. In addition, for those sharp-transitioned dichromatic illuminations, the illumination that more easily gets adapted tends to have a higher contribution to the adapted white point than the other one. A more comprehensive CAT model for dichromatic illuminations was derived from the collected visual data.

Multi illumination color constancy based on multi-scale supervision and single-scale estimation cascade convolution neural network.

Color constancy methods are generally based on a simplifying assumption that the spectral distribution of a light source is uniform across scenes. However, in reality, this assumption is often violated because of the presence of multiple light sources, that is, more than two illuminations. In this paper, we propose a unique cascade network of deep multi-scale supervision and single-scale estimation (CN-DMS4) to estimate multi-illumination. The network parameters are supervised and learned from coarse to fine in the training process and estimate only the final thinnest level illumination map in the illumination estimation process. Furthermore, to reduce the influence of the color channel on the Euclidean distance or the pixel-level angle error, a new loss function with a channel penalty term is designed to optimize the network parameters. Extensive experiments are conducted on single and multi-illumination benchmark datasets. In comparison with previous multi-illumination estimation methods, our proposed method displays a partial improvement in terms of quantitative data and visual effect, which provides the future research direction in end-to-end multi-illumination estimation.

Reproductive Performance of Zi-Goose Promoted by Red Color Illumination.

The color of light affects the reproductive performance of poultry, but it is not clear what efficient illumination strategy could be adopted to improve the reproductive performance of Zi-goose. Red light can increase the average weekly egg production rate, egg production, and qualified production. It can increase the serum GnRH level and decrease the serum PRL, MT, and T4 levels. In our study, red light for 12 h increased the average weekly laying rate, average qualified egg production, and hatching rate of Zi-goose eggs, and increased the serum levels of FSH, LH, P4, E2, MT, T3, and T4. Blue light at 14 h improved the average weekly egg production rate, average egg production, and average qualified egg production, and reduce serum PRL and MT levels to ensure the improvement of reproductive performance of goose. A total of 705,714 overlapping group sequences, 471,145 transcript sequences, and 268,609 single gene sequences were obtained from 18 sequencing samples, with a total length of 323.04, 668.53, and 247.88 M, respectively. About 176,416 unigenes were annotated successfully in six databases, accounting for 65.68% of the total unigenes obtained. 2,106, 2,142, and 8,892 unigenes were identified in the hypothalamus, pituitary gland, and ovary of the birds respectively, with different expressions of light regulation. The hypothalamus, ovary, and pituitary were involved in 279, 327, and 275 KEGG (Kyoto Encyclopedia of Genes and Genomes) metabolic pathways in response to light, respectively. Through further significance analysis and differential discovery rate control, a total of five metabolic pathways were obtained which were closely related to the reproductive hormones of goose. Ten candidate genes related to the reproductive performance of goslings were selected according to the identification results of differentially expressed genes of goslings under red light and white light conditions and the genes involved in metabolic pathways significantly related to the reproductive hormones of goslings. The expression levels of GnRh-1 in the hypothalamus, GnRH-R, FSH β and LH β in the pituitary gland, and FSH-R and LH-R candidate genes in the ovary were higher under the 12 h red light treatment than white light. However, the expression levels of VIP, PRL, and PRL-R candidate genes in the hypothalamus, pituitary and ovary were lower under 12 h red light than under 12 h white light.

QRsens: Dual-purpose quick response code with built-in colorimetric sensors

QRsens represents a family of Quick Response (QR) sensing codes for in-situ air analysis with a customized smartphone application to simultaneously read the QR code and the colorimetric sensors. Five colorimetric sensors (temperature, relative humidity (RH), and three gas sensors (CO2, NH3 and H2S)) were designed with the aim of proposing two end-use applications for ambient analysis, i.e., enclosed spaces monitoring, and smart packaging. Both QR code and colorimetric sensing inks were deposited by standard screen printing on white paper. To ensure minimal ambient light dependence of QRsens during the real-time analysis, the smartphone application was programmed for an effective colour correction procedure based on black and white references for three standard illumination temperatures (3000, 4000 and 5000 K). Depending on the type of sensor being analysed, this integration achieved a reduction of ∼71 – 87% of QRsens's dependence on the light temperature. After the illumination colour correction, colorimetric gas sensors exhibited a detection range of 0.7–4.1%, 0.7–7.5 ppm, and 0.13–0.7 ppm for CO2, NH3 and H2S, respectively. In summary, the study presents an affordable built-in multi-sensing platform in the form of QRsens for in-situ monitoring with potential in different types of ambient air analysis applications.

Adaptive Display White Point for Enhancing Viewing Experience of Mixed Reality Headsets

The development of various new imaging systems introduces new viewing conditions that did not exist in the past. Mixed reality systems, which capture the real environment and renders the captured image on display with virtual objects superimposed, require more immersive and realistic feeling than virtual and augmented reality systems, especially when users just put on the headsets. Therefore, the rendering shown on the display needs to be carefully adjusted to match the appearance in the real environment. In this study, we specifically focus on reproducing the overall color tone of the real environment under different ambient illumination color by shifting the white point of the display. The human observers viewed a real environment under different ambient illumination conditions, in terms of CCT and chromaticities, and evaluated the rendering of the captured scene with 44 white points. The results clearly suggested that the display white point should be adaptive to the ambient illumination color, especially when the ambient illumination had a CCT below 4000 K, to provide a good user experience.

Effects of illuminance and color temperature of a general lighting system on psychophysiology while performing paper and computer tasks

This study provides optimal correlated color temperature and illuminance to increase comfort and reduce fatigue by considering psychological and physiological quantities when working with paper and electronic devices. Task performance was not affected by devices and lighting conditions. The subjective evaluation revealed no significant differences between devices. The participants felt tired with an illuminance of 300lx and preferred a correlated color temperature of 5000K or 6500K and an illuminance of 750lx. However, the participants were more comfortable at 3000K and 750lx than at high correlated color temperature and low illuminance. The adjustment method demonstrated that comfortable illuminance does not show a significant difference in correlated color temperature and that paper requires significantly higher brightness levels than a screen. The adjustment method and subjective evaluation found consistent results for comfortable illuminance. Physiological measurements revealed that oxygenated hemoglobin was higher for computer than for paper use. In addition, illuminance of 500lx and correlated color temperature of 5000K resulted in the least fatigue. Although the subjective evaluation found no significant differences in fatigue, physiological measurements revealed that illuminance and correlated color temperature were accompanied by the least fatigue. Therefore, the results of this study highlight the necessity of creating a work environment that considers psychological and physiological quantities based on the work medium.

The concentration effect of Ce3+ ions on the photoluminescence properties of the host sensitized NaMPO4-Ce3+ (M = Mg and Ca) phosphors via solid-state reaction method

A series of Ce3+ doped NaMPO4 (M = Mg and Ca) nanophosphors were prepared using the solid-state reaction route, annealed at 900 °C for 4 h (except for NaMgPO4 which was annealed at 780 °C for 4 h). In this study, the concentration effects of Ce3+ ions for x = 0.0, 0.1, 0.5, 1.0, 1.5 and 2.0 mol% were investigated for its structural and photoluminescence (PL) properties. The structural and PL properties of the NaMPO4:xCe3+ compounds were analyzed using different characterization techniques, such as X-Ray diffraction (XRD), Field Emission Scanning Microscopy (FE-SEM), UV–vis diffuse reflection spectroscopy (DRS), Fourier Transform Infrared Spectroscopy (FTIR), PL and International Commission on Illumination (CIE) colour coordinates. XRD results confirm the prepared phosphors were crystallized into monoclinic (NaMgPO4) and orthorhombic (NaCaPO4) structures. SEM results confirm that all prepared samples were formed in the micrometer dimension range, with different sizes and shapes. Energy dispersive X-ray spectroscopy (EDS) spectra confirm the presence of chemical elements in the prepared nanophosphors. The presence of all phosphate (PO43−) and other structural groups were confirmed through FTIR measurements. UV–vis DRS measurements were used to calculate the optical band gap energy values via the Kubelka-Munk function theory. The PLE spectra of the NaMPO4:xCe3+ phosphors were measured in the 200–300 nm range by monitoring their peak at the 385 nm emission wavelength. Using 281 nm excitation wavelength, the PL spectra were measured and a high intensity emission band was found at the 385 nm wavelength (violet colour region). Using PL data of all NaMPO4:xCe3+ ion nanophosphors, the CIE colour coordinates were calculated and were found to lie in the violet colour region of the CIE colour diagram. From all the PL results, it is noticed that enhanced violet colour emissions were observed for all NaMPO4:xCe3+ compounds with increasing Ce3+ ion concentrations, implying that NaMPO4:xCe3+ phosphors are potential candidates for violet colour emitting technologies in display systems.

Color appearance of color chips under light‐emitting diodes lamps part II: Hue shift direction

AbstractOur previous experiment showed that the color appearance of color chips changes depending on the color of illumination. In this article, we continued to analyze the previous data of 23 color chips under six vivid colored illuminations (red, yellow, green, cyan, blue, and magenta) that were assessed by 100 subjects. We found that there were usually two directions of shifted color under vivid illumination. For example, color chips would change to either a dark blue or orange direction under vivid red illumination depending on the color of the color chips. We also found that there is a similar mechanism behind the chromatic adaptation in relation to the complementary color.