Search

Makeup transfer is the task of applying on a source face the makeup style from a reference image. Real-life makeups are diverse and wild, which cover not only color-changing but also patterns, such as stickers, blushes, and jewelries. However, existing works overlooked the latter components and confined makeup transfer to color manipulation, focusing only on light makeup styles. In this work, we propose a holistic makeup transfer framework that can handle all the mentioned makeup components. It consists of an improved color transfer branch and a novel pattern transfer branch to learn all makeup properties, including color, shape, texture, and location. To train and evaluate such a system, we also introduce new makeup datasets for real and synthetic extreme makeup. Experimental results show that our framework achieves the state of the art performance on both light and extreme makeup styles. Code is available at https://github.com/VinAIResearch/CPM.

The color scheme plays an important role in different aspects of our everyday lives, such as web design and human-computer interaction. The generation of color scheme requires a long-term accumulation of design experience and advanced knowledge of color matching. However, there is little work focusing on the automatic generation of color scheme based on learning capabilities. In this work, we propose a novel color scheme designer, SmartColor, which incorporates deep learning methods with knowledge of color psychology. The Generative Adversarial Network (GAN) is used to learn experienced insights from widely recognized color schemes obtained from online color matching websites. Color schemes based on various themes are transformed as statistical constraints in the construction of the objective function of GAN. SmartColor is both data-driven and knowledge-driven. In contrast to current color scheme solutions. SmartColor will automatically create color schemes based on the input theme. Experimental results show that SmartColor was successful in creating color schemes for websites.

Aiming at the behavioral characteristics of patients with Alzheimer's disease (AD), this paper explored the spatial environment that was helpful for their rehabilitation treatment through the orientated spatial design and their behavioral characteristics. The movement streamline, functional layout, display decoration, color matching and intelligent application of space was taken as consideration factors, then, an in-depth study was conducted from the three main behavioral characteristics: patients roaming and wandering, sitting silent and cognitive decline, and followed by the exploration of the unconscious treatment design method of spatial environment.

In order to explore the evaluation method of black fabric, this paper uses computer color measurement and color matching technology to select two kinds of polyester knitted white fabrics as raw materials, and utilizes black tubes as standard samples to prepare polyester knitted printed black fabrics. The samples are compared and sorted, and the characteristics of each indicator are analyzed. The results show that it is apt to directly characterize the blackness of polyester knitted printing fabric by DE* value; σ b has a reference significance for determining the end value of blackness within a certain range, but when the reflectance value is very low, the difference between different black fabrics is not very obvious.Gray-scale image-assisted visual evaluation can help observers more objectively evaluate blackness, and can achieve a natural transition from the machine to the human eye, which can reduce visual errors to a certain extent.

This paper we proposed a vision-based square puzzle reconstruction method using the color compatibility feature. Using similarity equation via Hausdorff-based border compatibility, the best piece of a puzzle can be obtained to form the initial combination by calculating the similarity of adjacent pieces and completing the puzzles after three combinations. Based on the experimental results tested on 25 images where classified into 35-piece and 70-piece puzzles, the average success rate reached 87.1% and 17 of the 35-piece puzzles were solved with 100% accuracy. For the class of 70 pieces, 77.8% was obtained on average, and 13 of them were solved with 100% accuracy.

This paper investigated the influence of Color Rendering Index on emotion and visual fatigue. By comparing the impact of different CRI and GAI values on the color perception and emotions, getting the recommended values of CRI and GAI in the office environment. In this experiment, GAI was used to assist Ra to evaluate the relationship of color rendering index with emotion and visual fatigue. The test methods used in the experiment include color matching, critical flicker frequency test, and emotion and fatigue scales, through which the experiment was conducted in different ways ranging from physiological indicators, eye fatigue indicators, emotional and fatigue scales. The experimental results were analyzed by (ANOVA) variance analysis, (PCA) principal component analysis, mean-value analysis, repeated measurement, and multivariate analysis. The results showed that the participants are most likely to produce positive emotions in the condition of GAI = 120, Ra = 80, and they are least likely to accumulate fatigue. Under GAI = 100, Ra = 100 cases, the mean value of the critical flicker frequency (CFF) difference is the smallest, and participants are not prone to fatigue. GAI has a certain influence on emotions, while the influence of Ra is smaller. Finally, GAI=100, Ra=100 and GAI=120, Ra=80 are easier to generate positive emotions.

Accurate measurement of the human skin color is very important in many multidisciplinary applications such as medicine for diagnostic purposes and prostheses color matching, cosmetology for makeup and skin care, computer graphics for skin rendering, and computer vision for skin detection and tracking. It must be noted that in a previous study we found that the Iranian skin colors are not truly encompassed by the Pantone SkinTone Guide, so the present study was carried out. In this research, a pilot dataset of Iranian skin color was collected to analyze its properties due to the variations in different parameters which affect the skin color and also to compare Iranian skin color gamut with different international ethnicities. The skin spectral data for a group of 60 subjects were taken at three reference locations on the face: the forehead, the left cheek, and the right cheek. The measurements were done using a spectrophotometer after filling in a questionnaire consists of a consent form in addition to name, gender, age, parent ethnicities, and blood type of the individuals. Afterward, the spectral data were converted into L* (Lightness), a* (Redness) and b* (Yellowness) color coordinates. These coordinate values of skin colors were analyzed according to gender, age, body part, and blood type. The results showed variations in skin color due to gender, age, body part, and ethnicity differences. Iranian males are found to have a little darker and more reddish and yellowish skin than females, and it is reported that the age increase causes a decrease in lightness and yellowness and an increase in redness for the collected data. Moreover, cheeks are identified lighter and less reddish than foreheads. A comprehensive skin color gamut is presented for Iranian population which can be used to develop a national skin color guide.

Comunicació presentada a: SMPTE 2017 Annual Technical Conference and Exhibition, celebrat del 23 al 26 d'octubre de 2017 a Los Angeles, Estats Units d'Amèrica. In cinema and TV it is quite usual to have to work with footage coming from several cameras, which show noticeable color differences among them even if they are all the same model. In TV broadcasts, technicians work in camera control units so as to ensure color consistency when cutting from one camera to another. In cinema post-production, colorists need to manually colormatch images coming from different sources. Aiming to help perform this task automatically, the Academy Color Encoding System (ACES) introduced a color management framework to work within the same color space and be able to use different cameras and displays; however, the ACES pipeline requires to have the cameras characterized previously, and therefore does not allow to work ‘in the wild’, a situation which is very common. We present a color stabilization method that, given two images of the same scene taken by two cameras with unknown settings and unknown internal parameter values, and encoded with unknown non-linear curves (logarithmic or gamma), is able to correct the colors of one of the images making it look as if it was captured with the other camera. Our method is based on treating the in-camera color processing pipeline as a combination of a 3x3 matrix followed by a non-linearity, which allows us to model a color stabilization transformation among two shots as a linear-nonlinear function with several parameters. We find corresponding points between the two images, compute the error (color difference) over them, and determine the transformation parameters that minimize this error, all automatically without any user input. The method is fast and the results have no spurious colors or spatio-temporal artifacts of any kind. It outperforms the state of the art both visually and according to several metrics, and can handle very challenging real-life examples. This work was supported by the European Research Council, Starting Grant ref. 306337, by the Spanish government and FEDER Fund, grant ref. TIN2015-71537-P(MINECO/FEDER,UE), and by the Icrea Academia Award. The work of J. Vazquez-Corral was supported by the Spanish government under Grant IJCI-2014-19516.

This article deals with tracking of laboratory animals (guinea pigs) in cage. Authors collective applied machine vision tools based on global automatic thresholding, adaptive thresholding, differential operators and color matching algorithms. Animal activity and trajectory is significant marker in research of selected pathologies (gastrointestinal diseases in our case). Tracking is done in the huge database of videosequences of healthy animals (reference) and animals with induced gastric pain (gastric ulcer). The solution also be used like non-expensive replacement of radio-frequency laboratory trackers.

The introduction of high-dynamic-range (HDR) color spaces and ultra-high-definition's (UHD) wide-color-gamut (WCG) color space in television creates a need to match colors on HDR and WCG displays with colors on conventional high-definition (HD) displays. Many contemporary color conversion methods that apply to conversion from HD to standard definition (SD), and color conversion methods mandated by current television standards, fail to produce a good color match when converting colors from the HDTV color space to HDR or WCG color spaces. This impairs the quality of HDTV contributions to HDR and UHD productions, as well as the quality of distribution of programs originating in HDR or UHD to HDTV viewers. This paper illustrates the color errors caused by the application of several of these conversion methods, and recommends one method, using display-referred colorimetry, for better color matching between narrow-gamut, wide-gamut and high-dynamic-range displays.

We aimed at making the color chart of new yellowish green grape cultivar "Shine Muscat" by using original color that was a useful and quantitative evaluation index of the appearance. The relationship between the ingredient changes and the color development of grape berries of "Shine Muscat" was also clarified. Accurate color information was obtained from the acquired berry image since the reflected glare of the optical diffusion body was suppressed on the surface of the fruit berry. Moreover, it was confirmed that color chart is a very useful tool to evaluate the introspectiveness quality of grape berry. The adoption of HSV color space that covers the human perceived color approximately and the color matching between monitor and printer enabled us to make the color chart with convenience and utility.

This work presents a Color Fuzzy Set Design procedure, or similarly a color naming procedure, based on the VITA Classical dental color shade guide, for composite color matching applications in direct restorations in aesthetic dentistry. For that purpose, a psychophysical experience based on a set of visual assessments by a panel of observers was performed, with the objective of identifying the areas of the CIELAB color space which can be associated to each shade of the VITA guide. A number of composite sets from four different manufacturing companies were used in the experiment. This information was processed and a set of nonparametric Fuzzy Sets was obtained for the VITA shades, with the aid of an acceptability dental color threshold taken from previous studies. The designed Fuzzy Set System was applied for the identification of the VITA shade of different dentine and enamel composite samples (bilaminar technique) from two different manufacturing companies, with the subsequent clinical applicability. Results show a high level of accuracy in VITA shade identification of the operated dental samples, when compared with visual assessment performed by experts.

Impression managements with fashion, cosmetics, hairstyle and hair-color etc. are omnipresent. Matching to the self-concept is the primary factor in impression managements. In the current research, we examined how hair-color matching evaluation would correlate with one's intended impressions to others and how the matching of hair-color might affect the self-perception in Japanese women. Results indicated that: 1) Hair-color matching evaluation by oneself was related to the one's intended impressions. 2) The colors that were thought to be matched to oneself were evaluated as socially desirable and interpersonally likeable. Thus, Japanese women want to make them appear "socially acceptable" and it is an important criterion for hair-color matching evaluation. This is consistent with the idea that motivation of managing impressions is to convey one's social roles in communities.

It cost much time to transfer color printed on paper or cloth by post office in traditional printing & dying industry. In this paper, we present a method of emending color measured by different spectrophotometers for computer-aided color matching. This method emends the color data measured by different spectrophotometers using PANTONE color cards as criterion to reduce color aberration while transferring color data from long-distance. By the method, the enterprise and customers can get available color data and the enterprise can use the amended color data for computer-aided color matching conveniently. It is proved that the method can help the printing & dying industry improve the effect of color transferring and make the industry more profitable.

In this paper, we have designed a gesture mouse system which is based on machine vision. Capturing image with a ordinary USB camera, it realize the mouse's click and movement by the method of template matching. It can control games by identifying users' gestures automatically. The system enables the users to interact with the computer in a more natural and intuitive way in real environment, and make the simple game more realistic.

Identifying individual cells in biomedical images is a challenging problem because of the staining, hardening, and slicing process. A lot of jobs have been done with sufficient staining so the interested cells can be extracted using HIS or other color matching method. When the staining is insufficient, the interested cells will be of the same color with others. Here we introduce a statistical method that can successfully identify leukocyte from others like red cell, intercellular space or megakaryocyte, and thus get the specific count. Learning is required to get the color specific statistical features of interested areas, further identification can be automatic for the whole page of image and the images from the same staining batch. The proposed method can be improved to count the percentage of the leukocytes from a marrow sample and served as an assistant diagnosis of leukemia.

In order to get the prediction of dyeing concentration on the value of fabric color, this paper establishes the mathematical model of RGB value and dyeing concentration based on the measured data. And then the minimum error average fitting method is used to calculate the function to get the prediction. The Newton iteration method is also used in solving the equation after the measured RGB data is substituted. And finally the dyeing concentration we need is found.

This paper presents a new keypoint-based approach to near-duplicate images detection. It consists of three steps. Firstly, the keypoints of images are extracted and then matched. Secondly, the matched keypoints are voted for estimation of affine transform based on an affine invariant ratio of normalized lengths. Finally, to further confirm the matching, the color histograms of areas formed by matched keypoints in two images are compared. This method has the advantage for handling the case when there are only a few matched keypoints. The proposed algorithm has been tested on Columbia dataset and conducted the quantitative comparison with RANdom SAmple Consensus (RANSAC) algorithm and Scale-Rotation Invariant Pattern Entropy (SR-PE) algorithm. The experiment result turns out that the proposed method compares favorably against the state-of-the-arts.

Obtaining the proofer's ICC profile and the reference ICC profile (or press ICC profile) is vital in establishing digital proofing environment. Generally, the press ICC profile is got by measuring a press sample including standard color patches. In this paper, a reversed method is put forward, in stead of printing standard chart, the real design pages and a few typical images are assembled and output both CTP plates and digital proof simulating a similar press ICC profile, the press ICC profile is got finally by several visual corrections. And in order to trace the changing of the printing process, the printing quality and ICC characteristics control strips are designed and renew the reference ICC profile all the time. Based on the new method of obtaining the press ICC profile, the digital proof has achieved a perfect color matching effect.

International audience; One of the basic tenets of conventional applied colorimetry is that the whole population of color normal observers can be represented by a single "standard" observer with reasonable accuracy. The 1964 CIE standard colorimetric observer has indeed served us well in all industrial color imaging applications, until recently. With the proliferation of modern wide-gamut displays with narrow-band primaries, color scientists and engineers face a new challenge. Various recent studies, including those by the current authors, have shown that the color perception on such displays varies significantly among color normal observers. Conventional colorimetry has no means to predict this variation. In this paper, we explore this problem by summarizing the results from an ongoing study, and explain the practical significance of this issue in the context of display applications.

This paper studied a kind of wood dyeing pigment formula prediction model built by using dynamic fuzzy neural network. The relative error of this prediction model was 0.52% and its training time was 128s. The results were comparatively satisfactory. This method provided a new way for wood dyeing and color matching and a new idea for the applications of its theories in color matching system, so it had certain theoretical research and practical application value.

The success of automobile's design is determined by three main factors: users, markets and their coordination. This study, by conducting the color image scale experiment, the market potential experiment and users' preference experiment, found that 1) users' cognition about automobiles' color image were different very much, 2) the automobiles with good market potential did not lie in the scopes of users' ideal color image all, and 3) the samples users liked were the same as the ones with good market potential. This study, by a new creative method, integrated users' preference, market potential and color image scale into automobile's color matching, and offered a case to confirm this method.

When images are stitched together to form a panorama there is often color mismatch between the source images due to vignetting and differences in exposure and white balance between images. In this paper a low complexity method is proposed to correct vignetting and differences in color between images, producing panoramas that look consistent across all source images. Unlike most previous methods which require complex non-linear optimization to solve for correction parameters, our method requires only linear regressions with a low number of parameters, resulting in a fast, computationally efficient method. Experimental results show the proposed method effectively removes vignetting effects and produces images that are highly visually consistent in color and brightness.

The modeling and problem solving for color matching in textile dyeing are discussed in this paper. Considering the poor effect and precision of the traditional textile dyeing color matching method and the non-linearity and uncertainty in color matching process for textile dyeing, a computer color matching method by numerical analysis is proposed and a mathematic model based on the mixtures of three colorants is established. By doing data fitting and using Newton-Krylov algorithm the solution of dye recipes can be got. This method has showed a prospective use in color matching for textile dyeing not only for its easy understanding but also for its better accuracy.

Purpose was to determine whether our developed electrophysiological technique (Momose and Saito, 2002) using visually evoked potential (VEP) is effective for determining the color discrimination threshold in human. Both VEP and psychophysical color matching measurement were applied to three normal volunteers, and their correlation and sensitivity were investigated. Colors on the MacAdam ellipse were selected for stimulus. Threshold determined by VEP was well correlated with psychophysical measure (r = 0.88 and 0.75 in two subjects), and was about 24 times higher than psychophysical ones. VEP measurement was done within much shorter time (30 min.) than psychophysical method (3 hours). VEP determined color discrimination threshold can be effective for the human color vision testing.

The dither matrix has been extensively applied in image processing, color matching and other aspects. In the paper, a new concept is put forward about the generalized Latin square and a mathematical description of the dither matrix, the counting formula of the generalized Latin square and a pair of orthogonal generalized Latin squares are given. The necessary and sufficient conditions of two orthogonal generalized Latin squares are presented and one-to-one correspondence relation of two sets between dither matrix and a pair of orthogonal generalized Latin squares are established by studying the generalized Latin squares. So the study of dither matrix can be transformed to that of a pair of orthogonal generalized Latin squares.