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

Abstract

To recognize the layout of color yarns of single-system-m elange 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-m elange color fabrics with satisfactory accuracy and good robustness.

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

“…In the proposed method, Savitzky–Golay filter is applied to smooth the projection curves and m is an important parameter to control the smoothing span: m = d × γ 1 . Furthermore, in the step of variance curve calculating, n is an important parameter to control the span of calculating variance: n = d × γ 2 , where d is the warp width d warp or weft width d weft that can be inspected by the yarn segmentation method . Thus, γ 1 and γ 2 are the key parameters to decide the difference between the peak values and other values in the variance curve, which exercise a great influence on the fabric segmentation result.…”

“…Based on the region segmentation results, the completed white warp and weft regions in sample 16 can be extracted and labeled as orange and green strips, respectively, whereas the black regions cannot be taken into consideration. The layout of the color warps and wefts are recognized by applying the inspection method into the extracted regions, as shown in Figs. (b) and (c).…”

“…To inspect the layout of color yarns, the yarn‐dyed fabrics are divided into two categories: double‐system‐mélange and single‐system‐mélange color fabrics, according to the yarn colors in the fabric. The layout of color yarns has been detected for single‐system‐mélange color fabrics in Part I of this series of studies . Nevertheless, the automatic inspection of the layout of color yarns for double‐system‐mélange color fabrics has not been realized.…”

An intelligent system for fashion colour prediction based on fuzzy C‐means and gray theory

“…Effective colour clustering and substituting the data in prediction models is the main focus of this study, and hence how to retrieve optimal clustering result is of importance. Automatic colour cluster analysis is usually suitable for classifying thread images into different colours, for instance, histogram clustering, FCM and X‐means algorithms . FCM is a cluster analysis technology that categorizes vague degree in related elements and clusters the optimal classifying results.…”

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

“…To inspect the layout of color yarns of different yarn‐dyed fabrics, the yarn‐dyed fabrics are classified into two categories: double‐system‐mélange and single‐system‐mélange color fabrics, according to the types of color yarn in the fabric image . The layout of color yarns has been recognized for single‐system‐mélange color fabrics by the FCM‐based stepwise classification method in Part I of the series of studies, and the region segmentation has been realized by the projection‐based region segmentation method for double‐system‐mélange color fabrics in Part II of the series of studies . In this study, we focus on the layout of color yarns recognition for double‐system‐mélange color fabrics and the analysis and discussion of the proposed method.…”