Appearance change for colored spun yarn fabric based on image color transfer

Abstract

The fabric of colored spun yarn has ever-changing appearances and styles with different fancy yarns. The fabric image is commonly designed by the designer using the software, which needs complex user interactions and difficult image segmentation. In this paper, a modified color transfer method was proposed to generate the fabric appearance of colored spun yarn. Given the color card as the target image, the style fabric image was matched as the reference image based on the dominant luminance. After transferring the two images to lαβ color space, Wavelet transform and luminance sampling were utilized to filter the redundant high-frequency information and select the representative pixels, respectively. Then, the chromatic channels were transferred based on the best matched luminance and the neighborhood relation. Finally, the image after color transfer was reconstructed by wavelet reconstruction. The proposed reference image matching maintained the result to be the ground truth. For the samples selected, the combined methods based on wavelet transform and luminance sampling improved the efficiency and performance of the proposed scheme. Experiments were conducted on different fabrics with different colors and styles. Experiments demonstrated the validity and superiority of the proposed method, which can provide referential assistance for the designer and save considerable amounts of labor.

Appearance generation for colored spun yarn fabric based on conditional image‐to‐image translation

“…Actually, adequate paired one‐to‐one images of colored spun yarn fabrics are difficult to collect. Thus, the appearance change method 3 was implemented using the images of color cards and style fabrics to generate paired fabric images. Due to the appearance change results are depended on the reference image, the results were evaluated by the experts in the factory to select realistic images.…”

“…To holistically evaluate the visual quality of the generated images, two metrics including visual inspection and category probability were adopted to evaluate the color similarity and the category similarity, respectively. Referred to the five‐point similar scale, 3 the visual inspection was performed by three experts who work in the factory and have extensive experience. The five‐point similar scale is illustrated in Figure 6.…”

“…Traditionally, professional software assists designers to simulate the appearance of fabrics to satisfy customers' expectations, 2 but the repeated process is time‐consuming and requires professional skills. The appearance change method 3 first draws on the experience of image color transfer methods to obtain the style fabric from the color card for colored spun yarn fabrics to facilitate the design process. A series of image perceptions can be generated fast and efficiently, but the transfer performance is affected by image luminance and the luminance of the reference image requires to be similar to that of the target image.…”

Establish intelligent detection system to evaluate the sugar smoking of chicken thighs

“…Color detection can be achieved by simply putting the colorimetric card beside the sample, which can effectively solve color identification ( Giuseppe et al, 2008 ; Reyescerecedo et al, 2018 ). So far, colorimetric cards are widely applied in daily life, such as biliary atresia ( Roberta et al, 2020 ), coral health assessment ( Bahr et al., 2020 ), GI bleeding assessment ( Gary R et al, 1995 ), spinning fabric color detection ( Zhang et al, 2021b ), and formaldehyde levels ( Vladimir et al, 2011 ). However, few articles combine machine vision technology with algorithms to develop colorimetric cards to identify the color of smoked meat products.…”

Study on color representation model and computer simulation of colored spun fabrics based on image translation model

“…1,2 This special inner structure is ultimately manifested as the complex and varied 'fancy' color effect of colored spun fabric, that is, the color texture of colored spun fabric. Combined with an improved color transfer algorithm, Zhang et al 12 utilized wavelet transform and luminance sampling to filter the redundant high-frequency information of fabric texture, realizing the simulation of colored spun fabric's different appearances. The results revealed that the proposed method can transfer the fabric appearance among different color cards and style fabrics, and shows more superiority than other color transfer methods in both the peak signalto-noise ratio (PSNR) and manual visual inspection evaluation indexes.…”