A new color space based on K-medoids clustering for fire detection

Pixel color has proven to be a useful and robust cue for detection of most objects of interest like fire. In this paper, a hybrid intelligent algorithm is proposed to detect fire pixels in the background of an image. The proposed algorithm is introduced by the combination of a computational search method based on a swarm intelligence technique and the Kemdoids clustering method in order to form a Fire-based Color Space (FCS), in fact, the new technique converts RGB color system to FCS through a 3*3 matrix. This algorithm consists of five main stages:(1) extracting fire and non-fire pixels manually from the original image. (2) using K-medoids clustering to find a Cost function to minimize the error value. (3) applying Particle Swarm Optimization (PSO) to search and find the best W components in order to minimize the fitness function. (4) reporting the best matrix including feature weights, and utilizing this matrix to convert the all original images in the database to the new color space. (5) using Otsu threshold technique to binarize the final images. As compared with some state-of-the-art techniques, the experimental results show the ability and efficiency of the new method to detect fire pixels in color images.

Color-space distortions following long-term occupational exposure to mercury vapor

Color vision was examined in subjects with long-term occupational exposure to mercury (Hg) vapor. The color vision impairment was assessed by employing a quantitative measure of distortion of individual and group perceptual color spaces. Hg subjects (n = 18; 42.1 +/- 6.5 years old; exposure time = 10.4 +/- 5.0 years; time away from the exposure source = 6.8 +/- 4.6 years) and controls (n = 18; 46.1 +/- 8.4 years old) were examined using two arrangement tests, D-15 and D-15d, in the traditional way, and also in a triadic procedure. From each subject`s `odd-one-out` choices, matrices of inter-cap subjective dissimilarities were derived and processed by non-metric multidimensional scaling (MDS). D-15d results differed significantly between the Hg-group and the control group (p < 0.05), with the impairment predominantly along the tritan axis. 2D perceptual color spaces, individual and group, were reconstructed, with the dimensions interpreted as the red-green (RG) and the blue-yellow (BY) systems. When color configurations from the Hg-group were compared to those of the controls, they presented more fluctuations along both chromatic dimensions, indicating a statistically significant difference along the BY axis. In conclusion, the present findings confirm that color vision impairments persist in subjects that have received long-term occupational exposure to Hg-vapor although, at the time of testing, they were presenting mean urinary concentration within the normal range for non-exposed individuals. Considering the advantages of the triadic procedure in clinical evaluation of acquired color vision deficiencies, further studies should attempt to verify and/or improve its efficacy.

Digital color reproduction on color television monitors

Color displays used in image processing systems consist of a refresh memory buffer storing digital image data which are converted into analog signals to display an image by driving the primary color channels (red, green, and blue) of a color television monitor. The color cathode ray tube (CRT) of the monitor is unable to reproduce colors exactly due to phosphor limitations, exponential luminance response of the tube to the applied signal, and limitations imposed by the digital-to-analog conversion. In this paper we describe some computer simulation studies (using the U*V*W* color space) carried out to measure these reproduction errors. Further, a procedure to correct for color reproduction error due to the exponential luminance response (gamma) of the picture tube is proposed, using a video-lookup-table and a higher resolution digital-to-analog converter. It is found, on the basis of computer simulation studies, that the proposed gamma correction scheme is effective and robust with respect to variations in the assumed value of the gamma.

Skin Color-Based Video Segmentation under Time-Varying Illumination

A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin-color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and predictions of the Markov model. The evolution of the skin-color distribution at each frame is parameterized by translation, scaling and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and resampling the histogram. The parameters of the discrete-time dynamic Markov model are estimated using Maximum Likelihood Estimation, and also evolve over time. The accuracy of the new dynamic skin color segmentation algorithm is compared to that obtained via a static color model. Segmentation accuracy is evaluated using labeled ground-truth video sequences taken from staged experiments and popular movies. An overall increase in segmentation accuracy of up to 24% is observed in 17 out of 21 test sequences. In all but one case the skin-color classification rates for our system were higher, with background classification rates comparable to those of the static segmentation.

Estimation and Prediction of Evolving Color Distributions for Skin Segmentation Under Varying Illumination

A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and based on predictions of the Markov model. The evolution of the skin color distribution at each frame is parameterized by translation, scaling and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and re-sampling the histogram. The parameters of the discrete-time dynamic Markov model are estimated using Maximum Likelihood Estimation, and also evolve over time. Quantitative evaluation of the method was conducted on labeled ground-truth video sequences taken from popular movies.

An efficient particle filter for color-based tracking in complex scenes

In this paper, we introduce an efficient method for particle selection in tracking objects in complex scenes. Firstly, we improve the proposal distribution function of the tracking algorithm, including current observation, reducing the cost of evaluating particles with a very low likelihood. In addition, we use a partitioned sampling approach to decompose the dynamic state in several stages. It enables to deal with high-dimensional states without an excessive computational cost. To represent the color distribution, the appearance of the tracked object is modelled by sampled pixels. Based on this representation, the probability of any observation is estimated using non-parametric techniques in color space. As a result, we obtain a Probability color Density Image (PDI) where each pixel points its membership to the target color model. In this way, the evaluation of all particles is accelerated by computing the likelihood p(z|x) using the Integral Image of the PDI.

Color Segmentation using LVQ-Learning Vector Quantization

This thesis aims to present a color segmentation approach for traffic sign recognition based on LVQ neural networks. The RGB images were converted into HSV color space, and segmented using LVQ depending on the hue and saturation values of each pixel in the HSV color space. LVQ neural network was used to segment red, blue and yellow colors on the road and traffic signs to detect and recognize them. LVQ was effectively applied to 536 sampled images taken from different countries in different conditions with 89% accuracy and the execution time of each image among 31 images was calculated in between 0.726sec to 0.844sec. The method was tested in different environmental conditions and LVQ showed its capacity to reasonably segment color despite remarkable illumination differences. The results showed high robustness.

Color detection and segmentation for road and traffic signs

This paper aims to present three new methods for color detection and segmentation of road signs. The images are taken by a digital camera mounted in a car. The RGB images are converted into IHLS color space, and new methods are applied to extract the colors of the road signs under consideration. The methods are tested on hundreds of outdoor images in different light conditions, and they show high robustness. This project is part of the research taking place in Dalarna University / Sweden in the field of the ITS.

Fuzzy clustering of color and texture features for image segmentation: a study on satellite image retrieval

In this paper, a new image segmentation approach that integrates color and texture features using the fuzzy c-means clustering algorithm is described. To demonstrate the applicability of the proposed approach to satellite image retrieval, an interactive region-based image query system is designed and developed. A database comprising 400 multispectral satellite images is used to evaluate the performance of the system. The results are analyzed and discussed, and a performance comparison with other methods is included. The outcomes reveal that the proposed approach is able to improve the quality of the segmentation results as well as the retrieval performance.

A new beta-diketone complex with high color purity

In this work a new europium (III) complex with the following formula NH(4) [Eu(bmdm)(4)] was synthesized and characterized. The bmdm (butyl methoxy-dibenzoyl-methane) is a P-diketone molecule used as UV radiation absorber in sunscreen formulations. Coordination of this ligand to the Eu(3+) ion was confinned by FT-IR, while the Raman spectrum suggests the presence of NH(4)(+) ions. The photoluminescence spectra present narrow lines arising from f-f intra-configurational transitions (5)D(0-)(7)F(0,1,2,3,4), dominated by the hypersensitive (5)D(0)-(7)F(2) transition. In the spectrum recorded at 77 K, all transitions split into 2J + 1 lines suggesting that there is just one symmetry site around Eu(3+) ion. This symmetry is not centrosymmetric. The calculated intensity parameters are ohm(2) = 30.5 x 10(-20) cm(2) and ohm(4) = 5.91 x 10(-20) cm(2) for this complex. The CIE chromaticity coordinates (x = 0.67 and y = 0.32) show a dominant wavelength of 615 nm. The color gamut achieved by this complex is a 100% in the CIE color space. (c) 2005 Elsevier B.V. All rights reserved.

Color vision loss in patients treated with chloroquine

Pacientes que fazem uso de cloroquina ou hidróxi-cloroquina, drogas que são freqüentemente administradas para o tratamento de artrite reumatóide, lúpus eritrematoso ou malária, podem sofrer alterações na visão de cores e na sensibilidade de contraste. O presente estudo avaliou a função visual destes pacientes em um estudo conjunto da Universidade de São Paulo (USP), em São Paulo, e da Universidade Federal do Pará (UFPA), em Belém. Trinta e dois pacientes usuários de cloroquina sem alterações no exame de fundo de olho foram avaliados em São Paulo (n=10, 38 a 71 anos, média=55,8 anos) e em Belém (n=22, 20 a 67 anos, média=40 anos). A dose acumulada de cloroquina prescrita foi de 45 a 430 g (média=213 g; dp=152 g) para o grupo de São Paulo, e de 36 a 540 g (média=174 g; dp=183 g) para o grupo de Belém. Os testes foram realizados monocularmente com o estado refracional corrigido. A discriminação de cor foi avaliada utilizando o Teste de Cor de Cambridge (CCT): o limiar de discriminação de cor foi mensurado primeiro nos eixos protano, deutano e tritano, e em seqüência, três elipses de MacAdam foram determinadas. A visão de cores dos pacientes também foi avaliada com testes de arranjo de cores: o teste de 100 matizes de Farnsworth-Munsell (FM100), o D15 de Farnsworth-Munsell, e o teste Lanthony Dessaturado (D15d). A sensibilidade de contraste foi também medida com grades senoidais preto-e-brancas em 22 pacientes. Os resultados foram comparados com controles sem patologias oftalmológicasou neuro-oftalomológicas. 24 pacientes apresentaram discromatopsia adquirida, com perdas seletivas (11 pessoas) ou difusas (13 pessoas). Embora as perdas estivessem presentes no FM100, não houve correlação entre o escore de erro do FM100 e a área elíptica medida pelo CCT. Além disso, três pacientes que tiveram escores normais no FM100 falharam para alcançar limiares normais no CCT. O teste de Lanthony foi menos sensível do que os outros dois testes, tal que falhou em indicar perda em cerca de metade dos pacientes afetados, e o D15 foi o teste menos sensível, deixando de indicar déficits em 9 de 10 pacientes. A sensibilidade de contraste esteve dentro dos valores normais para pacientes submetidos a este teste. A extensão das perdas na discriminação de cores foi positivamente correlacionada com a dose acumulada. O CCT é recomendado para o acompanhamento destes pacientes, pois forneceu dados quantitativos que podem ser diretamente interpretados no espaço cromático da CIE (Commission Internationelle d'Éclairage).

Yolks color definition by supplementing yellow and red xanthophylls to hen's diets

Egg yolk color may be controlled both by the concentration and the type of xanthophylls added to diets, with the aim of meeting consumers demand. The objectives of this work were to study how yellow and red xanthophylls present in laying hens` diets influence yolks colors and find the concentrations of these ingredients that meet the regional consumer desire. A factorial design 5 x 3 with 5 concentrations of yellow xanthophylls (lutein + zeaxantin 40%; 1.0, 1.25, 1.5, 1.75 and 2.0 mg/hen/d) and 3 concentrations of red xanthophylls (canthaxantin 10%; 0, 0.35, 0.7 mg/hen/d) was used. After a 30 d period receiving corn basal diets and water ad libitum, 60 White Dekalbe hens were distributed to receive the 15 dietary treatments in 4 replicates. Diets were provided daily at 110 g, during 21 d under 16 h light/8 h dark. Yolks colors were evaluated daily using the CIE L, a, b color space and the Roche color index. After the color stabilization, data were analyzed by ANOVA, regression analysis and Response Surface Methodology (MRS). Global acceptance for the Roche colors was evaluated with a 5 points hedonic scale and data were analyzed by Friedman and Dunn tests. Significance was established at 95% (P < 0.05). Regression analysis showed that the red xanthophylls content was the most important factor that defined L, a and b values for yolk color (P < 0.0001; square function), although its effect was significantly affected by the yellow xanthophylls contents (P = 0.0277; P < 0.0001; P = 0.0002 for L, a, b, respectively), providing evidence for a synergistic effect and not for a saturation effect. MRS showed that the highest redness of yolks was reached with 1.5 mg/hen/d of yellow and 0.5 mg/hen/d of red xanthophylls. So, higher supplementations aiming at increasing yolk color would bring an unnecessary cost to the ration. The most accepted yolk color scored 9, which corresponded to mean color attributes L = 65; a = 16; and b = 64. MRS showed that these values could be reached with combinations of yellow:red xanthophylls like 1.0:0.15 or 1.5:0.1 mg/ hen/d or simply with the yellow xanthophylls at 2.0 mg/hen/d. So, it was concluded that both yellow and red xanthophylls are important to define yolks color; that high amounts of xanthophylls are unnecessary to bring changes to color; and that Brazilian consumer requires yolks color attainable with few amounts of red xanthophylls or only with the yellow ones.

A Comparative Evaluation of Three Skin Color Detection Approaches

Skin segmentation is a challenging task due to several influences such as unknown lighting conditions, skin colored background, and camera limitations. A lot of skin segmentation approaches were proposed in the past including adaptive (in the sense of updating the skin color online) and non-adaptive approaches. In this paper, we compare three skin segmentation approaches that are promising to work well for hand tracking, which is our main motivation for this work. Hand tracking can widely be used in VR/AR e.g. navigation and object manipulation. The first skin segmentation approach is a well-known non-adaptive approach. It is based on a simple, pre-computed skin color distribution. Methods two and three adaptively estimate the skin color in each frame utilizing clustering algorithms. The second approach uses a hierarchical clustering for a simultaneous image and color space segmentation, while the third approach is a pure color space clustering, but with a more sophisticated clustering approach. For evaluation, we compared the segmentation results of the approaches against a ground truth dataset. To obtain the ground truth dataset, we labeled about 500 images captured under various conditions.

Color uniformity in spotligths - visual perception and system design

La iluminación con diodos emisores de luz (LED) está reemplazando cada vez en mayor medida a las fuentes de luz tradicionales. La iluminación LED ofrece ventajas en eficiencia, consumo de energía, diseño, tamaño y calidad de la luz. Durante más de 50 años, los investigadores han estado trabajando en mejoras LED. Su principal relevancia para la iluminación está aumentando rápidamente. Esta tesis se centra en un campo de aplicación importante, como son los focos. Se utilizan para enfocar la luz en áreas definidas, en objetos sobresalientes en condiciones profesionales. Esta iluminación de alto rendimiento requiere una calidad de luz definida, que incluya temperaturas ajustables de color correlacionadas (CCT), de alto índice de reproducción cromática (CRI), altas eficiencias, y colores vivos y brillantes. En el paquete LED varios chips de diferentes colores (rojo, azul, fósforo convertido) se combinan para cumplir con la distribución de energía espectral con alto CRI. Para colimar la luz en los puntos concretos deseados con un ángulo de emisión determinado, se utilizan blancos sintonizables y diversos colores de luz y ópticas secundarias. La combinación de una fuente LED de varios colores con elementos ópticos puede causar falta de homogeneidad cromática en la distribución espacial y angular de la luz, que debe resolverse en el diseño óptico. Sin embargo, no hay necesidad de uniformidad perfecta en el punto de luz debido al umbral en la percepción visual del ojo humano. Por lo tanto, se requiere una descripción matemática del nivel de uniformidad del color con respecto a la percepción visual. Esta tesis está organizada en siete capítulos. Después de un capítulo inicial que presenta la motivación que ha guiado la investigación de esta tesis, en el capítulo 2 se presentan los fundamentos científicos de la uniformidad del color en luces concentradas, como son: el espacio de color aplicado CIELAB, la percepción visual del color, los fundamentos de diseño de focos respecto a los motores de luz y ópticas no formadoras de imágenes, y los últimos avances en la evaluación de la uniformidad del color en el campo de los focos. El capítulo 3 desarrolla diferentes métodos para la descripción matemática de la distribución espacial del color en un área definida, como son la diferencia de color máxima, la desviación media del color, el gradiente de la distribución espacial de color, así como la suavidad radial y axial. Cada función se refiere a los diferentes factores que influyen en la visión, los cuales necesitan un tratamiento distinto que el de los datos que se tendrán en cuenta, además de funciones de ponderación que pre- y post-procesan los datos simulados o medidos para la reducción del ruido, la luminancia de corte, la aplicación de la ponderación de luminancia, la función de sensibilidad de contraste, y la función de distribución acumulativa. En el capítulo 4, se obtiene la función de mérito Usl para la estimación de la uniformidad del color percibida en focos. Se basó en los resultados de dos conjuntos de experimentos con factor humano realizados para evaluar la percepción visual de los sujetos de los patrones de focos típicos. El primer experimento con factor humano dio lugar al orden de importancia percibida de los focos. El orden de rango percibido se utilizó para correlacionar las descripciones matemáticas de las funciones básicas y la función ponderada sobre la distribución espacial del color, que condujo a la función Usl. El segundo experimento con factor humano probó la percepción de los focos bajo condiciones ambientales diversas, con el objetivo de proporcionar una escala absoluta para Usl, para poder así sustituir la opinión subjetiva personal de los individuos por una función de mérito estandarizada. La validación de la función Usl se presenta en relación con el alcance de la aplicación y condiciones, así como las limitaciones y restricciones que se realizan en el capítulo 5. Se compararon los datos medidos y simulados de varios sistemas ópticos. Se discuten los campos de aplicación , así como validaciones y restricciones de la función. El capítulo 6 presenta el diseño del sistema de focos y su optimización. Una evaluación muestra el análisis de sistemas basados en el reflector y la lente TIR. Los sistemas ópticos simulados se comparan en la uniformidad del color Usl, sensibilidad a las sombras coloreadas, eficiencia e intensidad luminosa máxima. Se ha comprobado que no hay un sistema único que obtenga los mejores resultados en todas las categorías, y que una excelente uniformidad de color se pudo alcanzar por la conjunción de dos sistemas diferentes. Finalmente, el capítulo 7 presenta el resumen de esta tesis y la perspectiva para investigar otros aspectos. ABSTRACT Illumination with light-emitting diodes (LED) is more and more replacing traditional light sources. They provide advantages in efficiency, energy consumption, design, size and light quality. For more than 50 years, researchers have been working on LED improvements. Their main relevance for illumination is rapidly increasing. This thesis is focused on one important field of application which are spotlights. They are used to focus light on defined areas, outstanding objects in professional conditions. This high performance illumination required a defined light quality including tunable correlated color temperatures (CCT), high color rendering index (CRI), high efficiencies and bright, vivid colors. Several differently colored chips (red, blue, phosphor converted) in the LED package are combined to meet spectral power distribution with high CRI, tunable white and several light colors and secondary optics are used to collimate the light into the desired narrow spots with defined angle of emission. The combination of multi-color LED source and optical elements may cause chromatic inhomogeneities in spatial and angular light distribution which needs to solved at the optical design. However, there is no need for perfect uniformity in the spot light due to threshold in visual perception of human eye. Therefore, a mathematical description of color uniformity level with regard to visual perception is required. This thesis is organized seven seven chapters. After an initial one presenting the motivation that has guided the research of this thesis, Chapter 2 introduces the scientific basics of color uniformity in spot lights including: the applied color space CIELAB, the visual color perception, the spotlight design fundamentals with regards to light engines and nonimaging optics, and the state of the art for the evaluation of color uniformity in the far field of spotlights. Chapter 3 develops different methods for mathematical description of spatial color distribution in a defined area, which are the maximum color difference, the average color deviation, the gradient of spatial color distribution as well as the radial and axial smoothness. Each function refers to different visual influencing factors, and they need different handling of data be taken into account, along with weighting functions which pre- and post-process the simulated or measured data for noise reduction, luminance cutoff, the implementation of luminance weighting, contrast sensitivity function, and cumulative distribution function. In chapter 4, the merit function Usl for the estimation of the perceived color uniformity in spotlights is derived. It was based on the results of two sets of human factor experiments performed to evaluate the visual perception of typical spotlight patterns by subjects. The first human factor experiment resulted in the perceived rank order of the spotlights. The perceived rank order was used to correlate the mathematical descriptions of basic functions and weighted function concerning the spatial color distribution, which lead to the Usl function. The second human factor experiment tested the perception of spotlights under varied environmental conditions, with to objective to provide an absolute scale for Usl, so the subjective personal opinion of individuals could be replaced by a standardized merit function. The validation of the Usl function is presented concerning the application range and conditions as well as limitations and restrictions in carried out in chapter 5. Measured and simulated data of various optical several systems were compared. Fields of applications are discussed as well as validations and restrictions of the function. Chapter 6 presents spotlight system design and their optimization. An evaluation shows the analysis of reflector-based and TIR lens systems. The simulated optical systems are compared in color uniformity Usl , sensitivity to colored shadows, efficiency, and peak luminous intensity. It has been found that no single system which performed best in all categories, and that excellent color uniformity could be reached by two different system assemblies. Finally, chapter 7 summarizes the conclusions of the present thesis and an outlook for further investigation topics.

Contribution of S opponent cells to color appearance

We measured the regions in isoluminant color space over which observers perceive red, yellow, green, and blue and examined the extent to which the colors vary in perceived amount within these regions. We compared color scaling of various isoluminant stimuli by using large spots, which activate all cone types, to that with tiny spots in the central foveola, where S cones, and thus S opponent (So) cell activity, are largely or entirely absent. The addition of So input to that from the L and M opponent cells changes the chromatic appearance of all colors, affecting each primary color in different chromatic regions in the directions and by the amount predicted by our color model. Shifts from white to the various chromatic stimuli we used produced sinusoidal variations in cone activation as a function of color angle for each cone type and in the responses of lateral geniculate cells. However, psychophysical color-scaling functions for 2° spots were nonsinusoidal, being much more peaked. The color-scaling functions are well fit by sine waves raised to exponents between 1 and 3. The same is true for the color responses of a large subpopulation of striate cortex cells. The narrow color tuning, the discrepancies between the spectral loci of the peaks of the color-scaling curves and those of lateral geniculate cells, and the changes in color appearance produced by eliminating So input provide evidence for a cortical processing stage at which the color axes are rotated by a combination of the outputs of So cells with those of L and M opponent cells in the manner that we postulated earlier. There seems to be an expansive response nonlinearity at this stage.