Automatic detection of layout of color yarns of yarn‐dyed fabric. Part 3: Double‐system‐Mélange color fabrics

Automat layout detection of color yarns is necessary for weaving and producing processes of yarn‐dyed fabrics. This study presents a novel approach to inspect the layout of color yarns of double‐system‐mélange color fabrics automatically, which is Part III of the series of studies to develop a computer vision‐based system for automatic inspection of color yarn layout for yarn‐dyed fabrics. The inspection of single‐system‐mélange color fabrics has been realized in Part I of the series of studies. Integrating the projection‐based region segmentation method proposed in Part I and the FCM‐based stepwise classification method proposed in Part II, the proposed approach is composed of three steps: (1) fabric region segmentation, (2) fabric region selection, and (3) layout of color yarns recognition. In the first step, the fabric regions are segmented by the projection‐based region segmentation method. In the second step, the reasonable fabric regions are selected by analyzing their color histograms and comparing their weft color's frequency. In the third step, the layout of color yarn is recognized by the FCM‐based stepwise classification method, and the precise layouts of color warps and wefts are produced. The experimental analysis proved that the proposed method can recognize the layout of color yarns of double‐system‐mélange color fabrics correctly by testing four different color fabrics and three pieces of same yarn‐dyed fabrics. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 250–260, 2017     

Automatic detection of layout of color yarns of yarn‐dyed fabric. Part 1: Single‐system‐mélange color fabrics

To recognize the layout of color yarns of single‐system‐mélange color fabric automatically, a novel FCM‐based stepwise classification method is proposed in this article. This method consists of three main steps: (1) warp yarn segmentation, (2) weft color recognition, and (3) the layout of color warps recognition. In the first step, the yarn segmentation method based on mathematical statistics of subimages is adopted to localize warp yarns preliminarily; and then the segmentation results of warp yarn are corrected by misrecognized‐boundary remove and missing‐boundary interpolation. In the second step, the weft color is extracted based on RGB color histograms of whole fabric image. In the third step, the pixels in each warp yarn are classified into two clusters by fuzzy C‐means clustering (FCM) algorithm in CIELAB color model separately, and the preliminary recognized layout of color warps is obtained. All warp colors are clustered by FCM algorithm in CIELAB color model again and the precise layout of color warps is output. The experimental and theoretical analysis proved that the proposed method can recognize the layout of color yarns of single‐system‐ mélange color fabrics with satisfactory accuracy and good robustness. © 2015 Wiley Periodicals, Inc. Col Res Appl, 40, 626–636, 2015     

Pattern‐driven color pattern recognition for printed fabric motif design

Pattern‐driven design method is an important data‐driven design method for printed fabric motif design in textiles and clothing industry. We introduce a novel framework for automatic design of color patterns in real‐world fabric motif images. The novelty of our work is to formulate the recognition of an underlying color pattern element as a spatial, multi‐target tracking, classification, segmentation and similarity association process using a new and efficient color feature encoding method. The proposed design method is based on pattern‐driven color pattern recognition and indexing from the element image database. A series of color pattern recognition algorithms are used for color and pattern feature extraction. The local statistical corner features and Markov random field model are used for motif unit tiling detection and conversion. The color feature encoding problem is modeled in a gray‐scale color difference optimization problem, which can be solved quickly by existing algorithms. Color pattern feature matching, segmentation and indexing techniques are then used to locate and replace the elements in the motif unit image with similar elements in the database. Experiments show that the approach proposed in this study is effective for color pattern recognition and printed fabric motif design.     

Analysis of spinning process parameters on development of spun‐dyed PET yarn using the Taguchi method

The yarn tenacity of a spun‐dyed yarn is predicted from the spinning conditions and other properties of the yarn are analyzed through the defined parameters using the Taguchi method. To develop a spun‐dyed yarn using the Taguchi method, four factors that can largely influence the yarn properties are selected. From the experimental design based on four factors, the processes are executed to produce the specific yarns whose properties are measured to analyze the relationship between the process conditions and their results. The target properties of a spun‐dyed yarn may be obtained through adjusting the spinning parameters that are related to the yarn properties by the Taguchi tool. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 102:1419–1427, 2006     

An unsupervised method for dominant colour region segmentation in yarn‐dyed fabrics

This paper presents a novel unsupervised approach to detect dominant colour regions standing out conspicuously in yarn‐dyed fabric images. For a dominant colour region of a yarn‐dyed fabric, measured by an imaging system, its individual yarn has an irregular three‐dimensional shape resulting in significant colour difference among pixels of the yarn. This difference leads to difficulty in segmenting yarns into dominant colour regions. A probabilistic model is proposed in this study to associate the colour of a dominant colour region with the colours of its yarns. Based on this model, the colour histograms of a dominant colour region are first estimated from those of yarns in a yarn‐dyed fabric image. Then, a hierarchical segmentation structure is devised to detect dominant colour regions in the image. Experimental results show that the proposed approach achieves satisfactory performance for dominant colour region segmentation in yarn‐dyed fabric images, with high computational efficiency.     

Automatic detection of layout of color yarns of yarn‐dyed fabric. Part 2: Region segmentation of double‐system‐Mélange color fabric

To detect the layout of color yarns automatically, a novel projection‐based fabric segmentation method is proposed to segment the double‐system‐mélange color fabric into several regions, which can be seen as single‐system‐mélange color fabrics. This method consists of five main steps: (1) yarn skew detection, (2) fabric image projecting, (3) projection curve smoothing, (4) variance curve calculating, and (5) curve peak confirmation. Based on the acquisition fabric image, the skew angles of warp and weft yarns are detected by Hough transform first. The projection curves of L, a, and b channels in Lab color model are generated and smoothed by Savitzky–Golay filter. The variance curves of L, a, and b are then calculated, and the peaks corresponding to the regional boundaries in each curve are detected. The regional boundaries are confirmed by synthesizing the curve peaks of L, a, and b. The experimental and theoretical analysis proves that the proposed method can segment the double‐system‐mélange color fabric into regions with satisfactory accuracy and good robustness. © 2015 Wiley Periodicals, Inc. Col Res Appl, 41, 626–635, 2016     

Three‐dimensional color prediction modeling of single‐ and double‐layered woven fabrics

In this research, the three‐dimensional structural and colorimetric modeling of three‐dimensional woven fabrics was conducted for accurate color predictions. One‐hundred forty single‐ and double‐layered woven samples in a wide range of colors were produced. With the consideration of their three‐dimensional structural parameters, three‐dimensional color prediction models, K/S‐, R‐, and L*a*b*‐based models, were developed through the optimization of previous two‐dimensional models which have been reported to be the three most accurate models for single‐layered woven structures. The accuracy of the new three‐dimensional models was evaluated by calculating the color differences ΔL*, ΔC*, Δh°, and ΔE_CMC(2:1) between the measured and the predicted colors of the samples, and then the error values were compared to those of the two‐dimensional models. As a result, there has been an overall improvement in color predictions of all models with a decrease in ΔE_CMC(2:1) from 10.30 to 5.25 units on average after the three‐dimensional modeling.     

Color analysis of natural colorant‐dyed fabrics

Colors from naturally dyed fabrics recently have attracted both consumers and manufacturers in fashion markets. Even though color attributes of the fabrics have been partially observed in some literature, a data base of colors for natural colorants in fabrics needs to be established and the colors to be characterized according to systematic color notations and tones in order to relate the traditional natural colors to contemporary color communication systems. Therefore, a study was performed to investigate color characteristics for a given large set of natural colorants‐dyed fabrics based on the Munsell color notations, to analyze their tones with relation to the notation such as hue, value, and chroma, and finally to identify the effects of mordanting, an important coloring auxiliary, on the colorimetric properties of the fabrics. As a result, the dominant hue for a total of 350 naturally dyed fabrics was yellowish families followed by reddish and purplish ones in the Munsell notation owing to the use of leaves and plant as usual natural dyestuff, which confirms the limit of color hues of the fabrics. Color value for most of naturally dyed fabrics was generally higher whereas the chroma was lower, which means that most of colors for naturally dyed fabrics tended to be bright and weak shaded. Grayish, light grayish, and soft tones were the main tones of natural colorant‐dyed fabrics. All of hue, value, and chroma were found as being influenced by mordanting in that more particularly; iron mordanting was likely to cause the decrease of both value and chroma for most of naturally dyed fabrics. These results could provide a systematic color data for naturally dyed fashion fabrics and suggest a future direction of color development for them. © 2008 Wiley Periodicals, Inc. Col Res Appl, 33, 148–157, 2008     

Crosscultural comparison of color terms and preference of persimmon‐dyed fabric,Galchon

This crosscultural study was aimed at correlating color emotions and preference for persimmon‐dyed cotton fabrics known as Galchon. Cotton fabrics were dyed with persimmon powder, in a range of shades, and in some cases were also iron mordanted. Textile and fashion students from Jeju National University in Korea and North Carolina State University (NCSU) in USA participated in the visual assessment of dyed samples and were asked to scale their visual experience and state their emotion and preference for the terms “Bright,” “Heavy,” “Soft,” “Strong,” “Deep,” and “Like.” Korean observers used “Strong” for iron‐mordanted Galchon, and American observers did not associate “Bright” or “Deep” with weakly dyed fabrics. In addition to the subjective terms described, the color preference for samples was quantified using their CIE colorimetric attributes. For Korean observers, the results indicate a correlation between L^* and “Bright,” whereas for Americans a stronger correlation was obtained against “Soft.” American observers' results also show a relationship between C^* and the term “Warm,” especially for dyeings of Galchon at high concentrations. It was also found that iron mordanting affected responses from both groups but only influenced the color preference of Korean observers. © 2015 Wiley Periodicals, Inc. Col Res Appl, 40, 592–604, 2015     

Color emotions for multi‐colored images

We investigate the emotional response to colors in ordinary multicolored images. In psychophysical experiments, using both category scaling and interval scaling, observers are asked to judge images using three emotion factors: activity, weight, and heat. The color emotion metric was originally developed for single colors, and later extended to include pairs of colors. The same metric was recently used in image retrieval. The results show that people in general perceive color emotions for multi‐colored images in similar ways, and that observer judgments correlate with the recently proposed method used in image retrieval. The intended usage is in retrieval systems publicly available on the Internet, where both the user and the viewing environment is unknown, which requires novel ways of conducting the psychophysical experiments. © 2010 Wiley Periodicals, Inc. Col Res Appl, 36, 210–221, 2011;     

Color evaluation of wool fabric dyed with Rhizoma coptidis extract

Berberine is the only cationic colorant of natural plant dyes, which lies in the roots of Rhizoma coptidis and stems of phellodendron. In this study, wool fabric was dyed with the extracts of R. coptidis. Color evaluation was characterized with ΔE, L*, a*, b*, c*, H⁰, K/S. Effects of mordant, extraction concentration, pH value of dye bath, and treatment temperature on color values were studied. Results indicated that wool fabrics dyed with mordant, or at higher temperature, or in alkali solution possessed deeper shades and darker colors. And the wool fabric showed good antibacterial property after dyeing with R. coptidis extracts. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 101: 3376–3380, 2006     

K‐M theory of fabric knitted by three‐channel rotor spun wool yarn

Two‐component and three‐component color blended yarns were spun by red, yellow, and blue wool slivers using a three‐channel rotor spun machine, and the corresponding plain fabrics were knitted. The color‐matching models of K‐M theory were built with the relative method and the least squares method, respectively. Colors and blending ratios of the fabrics were predicted by the model. The results showed that the average color differences of the samples predicted by the two methods are both about 1.0 and the mean value of the proportional error is below 3%. The least squares method has a better color‐matching effect for the three‐component sample, and the relative value method has better color‐matching results for the two‐component sample. When the tolerance range is 2.0, the pass rates of the samples predicted by either the relative value method or the least squares method reach 100%.     

Measuring linear density of threads in single‐system‐mélange color fabrics with FCM algorithm

According to the color yarns in the fabric, the fabrics can be divided into three categories: solid color fabrics, single‐system‐mélange color fabrics, and double‐system‐mélange color fabrics. The density of solid fabrics can be inspected with gray‐projection method or Fourier analysis method. But the methods cannot be applied to yarn‐dyed fabrics directly. A method for detecting the density of single‐system‐mélange color fabrics will be discussed in this article. By analyzing the pattern and color characters of single‐system‐mélange color fabrics, fuzzy C‐means algorithm is proposed to classify the colors in the fabric image based on CIELAB color space first. With the color segmentation results, the fabric can be divided into different blocks. The yarns can be located in different blocks with different average gray‐levels, and then the number of yarns can be counted in each block. The linear density of threads can be obtained by counting the yarns in a unit length finally. The experiment proved that the algorithm proposed in this study can inspect the density of single‐system‐mélange color fabric successfully. © 2012 Wiley Periodicals, Inc. Col Res Appl, 38, 456–462, 2013     

Color appearance modeling of bicolor striped woven fabrics considering neighboring color effects

In this article, the effect of the spatial and colorimetric attributes of neighboring color on color appearance shift in bicolor striped woven fabrics is investigated. A total of 240 test/neighboring woven color combinations were constructed in four different striped paradigms. Each test color in the combinations was visually assessed by 12 observer panels with the use of the magnitude estimation method estimating the magnitude of perceptual color attributes lightness, colorfulness, and hue. The visual estimates obtained were analyzed statistically by employing correlation and simple regression methods, and, as a result, the following significant neighboring color effects were detected and individually defined: (1) neighboring color's size, lightness, colorfulness, and hue on test color's lightness, (2) neighboring color's colorfulness and hue on test color's colorfulness, and (3) neighboring color's hue on test color's hue. Furthermore, through multiple regression analysis, color appearance models by which the lightness, colorfulness, and hue of bicolor woven fabrics can be predicted were derived. The predictive performance of the models was evaluated by calculating the difference between the visually estimated and the predicted color appearances, using ΔL*, ΔC*, Δh°, and ΔE_CMC(2:1). Among all the derived models, the model producing the smallest mean error was chosen as a final model, and its great accuracy in color appearance predictions was verified through further statistical evaluation. It is envisaged that the findings of this research are of benefit to design textile products with bicolor striped woven fabrics to have desired color appearances. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 512–521, 2017     

Colour preference for Taiwanese floral pattern fabrics

A psychophysical experiment was carried out to investigate factors affecting colour preference for Taiwanese floral pattern fabrics, as a case study of object colour preference. A total of 175 test images of Taiwanese fabrics were used as the stimuli presented on a calibrated computer display. The images were generated on the basis of 5 existing Taiwanese fabrics, each manipulated into 35 images by changing the fabric colour. The 35 colours were selected to cover the most frequently used colours for existing Taiwanese fabrics. The 175 test images were assessed by 76 Taiwanese observers in terms of 9 semantic scales, including Taiwanese style/non‐Taiwanese style, Japanese style/non‐Japanese style, splendid/plain, traditional/modern, active/passive, warm/cool, heavy/light, like/dislike and harmonious/disharmonious. The experimental results reveal two underlying factors: “Splendidness” and “Harmony.” The like/dislike response was found to highly correlate with harmonious/disharmonious, but have poor correlation with Taiwanese style/non‐Taiwanese style. The study also reveals several factors affecting colour preference for Taiwanese fabrics, including the interaction effect of colour and pattern, observer's general liking for the object, and the effect of user experience. These findings can help develop a more robust, comprehensive theory of object colour preference. © 2015 Wiley Periodicals, Inc. Col Res Appl, 41, 43–55, 2016     

Color prediction models for digital Jacquard woven fabrics

The current industry practice for producing jacquard fabrics uses computer‐aided design (CAD) systems that provide visual simulations of the final color appearance of actual fabrics prior to production. This digital process is fundamentally based on the prediction of combined weave‐color effects, which can be successfully achieved by accurate color mixing models and the structural details of the fabrics. With the accurate models used in CAD systems, designers would see simulations more closely resembling fabrics to be produced. By checking the previews, the designers can easily modify, that is, recolor, the designs on the display monitor without doing repetitive physical sampling with the adjustment of the weaves and the yarn colors. However, there is no ready applicable accurate color mixing model for woven structures and there has not been sufficient investigation of the color prediction despite its usefulness for the current digital CAD process. Our study investigated the, color prediction of jacquard woven fabrics designed based on the principle of optically subtractive color mixing with the use of CMY colors. The color prediction was firstly done through the application of the six color mixing models previously developed for various other applications including fiber blending and printing. The performance of each model was evaluated by calculating the difference between the predicted and the measured colorimetric data, using ΔE_CMC(2:1). The average color difference from the models was 11.93 ΔE_CMC(2:1), which is hardly acceptable in textile industry. In order to increase the accuracy in color prediction, the six models were then optimized. As a result, substantial improvements for all models were obtained with a decrease in color difference to 4.83 ΔE_CMC(2:1) on average after the optimizations. Among the six optimized color mixing models, the optimized Warburton‐Oliver model, that is, W‐O model, was found to have the lowest average ΔE_CMC(2:1) value of approximately equaling to 2, which is considered potentially useful to be applied to the current digital fabric color prediction. © 2015 Wiley Periodicals, Inc. Col Res Appl, 41, 64–71, 2016     

An efficient method for solid‐colour and multicolour region segmentation in real yarn‐dyed fabric images

This paper presents an efficient approach to solid‐colour and multicolour region segmentation in real yarn‐dyed fabric images. The approach is based on a novel model describing the spectral response of a multispectral imaging system to yarn‐dyed fabrics. The model indicates that solid‐colour regions cannot be distinguished from multicolour regions in terms of reflectance, tristimulus, or CIELAB values owing to a geometric term representing the influence of fabric surface condition on measured colours. The geometric term makes it difficult to determine the segmentation thresholds of CIEXYZ and CIELAB colour histograms. However, solid‐colour and multicolour regions can be detected in CIExyY space because chromaticity coordinates are impervious to the geometric term. The CIExyY histograms of a solid‐colour region accord with one Gaussian distribution, but those of a multicolour region accord with a combination of two Gaussian distributions. The CIEXYZ, CIELAB, and CIExyY colour distributions of both solid‐colour and multicolour yarn‐dyed fabrics were analysed in detail in simulation and real experiments. Experimental results show that solid‐colour yarn‐dyed regions can be distinguished from multicolour yarn‐dyed fabric regions by the shapes of CIExyY histograms, but cannot be distinguished by the shapes of CIEXYZ or CIELAB histograms.     

Color vision assessment‐2: Color assessment outcomes using single and multi‐test protocols

The main purpose of this study was to produce reliable, color assessment outcomes to examine the extent to which single and multi‐test protocols in use meet current clinical and occupational needs. The latter include the detection of small changes in chromatic sensitivity as the earliest signs of retinal and/or systemic disease, and the need to assess the class of color vision in congenital deficiency and to quantify severity of loss. Color vision was assessed using Ishihara (IH), Farnsworth Munsell D‐15, City University (CU, 2nd ed.) and Holmes‐Wright type A (HW‐A) lantern tests. All subjects also carried out Colour Assessment and Diagnosis and Nagel anomaloscope tests. The sample included 350 normal trichromats, 1012 deutans and 465 protans (age 31.1 ± 12.4, range 10‐65 years). The results reveal the trade‐off between sensitivity and specificity, depending on the number of errors accepted as a pass on the IH test. The D‐15 and CU tests pass all normals and almost 50% of subjects with color vision deficiency. The HW‐A lantern passes all normals, 22% of deutans and 1% of protans. The multi‐test protocols designed to identify protans and to pass only subjects with mild color loss, pass over 50% of protans and deutans. Many of the subjects who fail exhibit less severe loss of color vision than others who pass. When high sensitivity for detection of congenital deficiency is achieved, single‐test protocols fail many normal trichromats. Multi‐test protocols produce large variability and fail to achieve desired aims.     

Color breakup visibility thresholds for 2‐field sequential colors

Nowadays local primary desaturation has been proved to be an effective method to suppress the color breakup for field‐sequential‐color (FSC) displays. However, little attention has been focused on the interaction between various subfield colors and the color breakup visibility. In this article, a perception experiment was conducted with the help of a 120 Hz 2‐field FSC display to investigate the thresholds of color breakup visibility along different hue directions with a constant white point in the standard color space. The experimental results show that the color breakup visibility is various when using different subfield colors for temporal combination. A relative high threshold value or low sensitivity of color breakup visibility can be observed when subfield colors are chosen along the blue‐yellow direction while becoming perceptible easily along magenta‐cyan direction. The results and analysis of our experiments are promising to optimize the performance of local primary desaturation. Meanwhile, other applications using the temporal color fusion such as tunable lighting can also benefit from the conclusion of our work to suppress the color breakup effect.