Attention-aware color theme extraction for fabric images

Abstract

Color configuration plays an important role in art, design, and communication, which can influence the user’s experiences, feelings, and psychological well-being. It is laborious to manually select a color theme from scratch for handling large batches of images. Alternatively, it can inspire designers’ creations and save their time as well by leveraging the color themes in existing art works (e.g. fabric, paintings). However, it is challenging to automatically extract perceptually plausible color themes from fabric images. This paper presents a new automatic framework for extracting color themes from fabric images. A saliency map is built to help recognize the visual attention regions of the input image. Since the saliency map separates the image into visual attention regions (foreground) and non-visual attention regions (background), we respectively compute the dominant colors of these two regions, and merge them to form the initial target color theme based on certain rules. The dominant colors are extracted, accounting for the characteristics of the fabric and hue distributions of fabric images so as to acquire visually plausible results. Our method can be used to transfer colors between two fabric images for fabric color design. We tested our method thoroughly with various fabric images (e.g. cotton, silk, and linen) with different texture patterns (e.g. plain and twill). Experiments show that our method is more efficient and can generate more visually plausible results than state-of-the-art algorithms.

Nonparametric histogram segmentation-based automatic detection of yarns

“…According to equation (6), the smaller the value of e , the larger the rejection region of hypothesis H 0 , which means the more finely the histogram is divided. As the width of each yarn is substantially the same, the variance σ 2 of segment length is close to 0. Hence, the suitable parameter e* is the one that minimizes σ 2 , and the detection of yarn locations can be determined adaptively.…”

“…Image-processing technology is being used in the textile industry to gradually develop methods involving automation and intelligence. The technology is widely used in fabric design [1][2][3] and fabric quality inspection, such as estimating yarn densities [4][5][6][7] and identifying weave patterns of woven fabrics. [8][9][10] Here, yarn density is the numbers of warp/weft yarns in a unit length, and weave pattern is determined by yarn locations and the crossing rule of yarns.…”

NK-CDS: A Creative Design System for Museum Art Derivatives

“…After changing the color, the element image looks more vivid and suitable for mapping to a 3D model. Lots of researches have been done on processing color and detail features of the image [37]- [39]. One thing to note is that there is no algorithm suitable for all types of cultural relics.…”

Development of a machine learning model for extracting image prominent colors

“…Unfortunately, these methods do not always guarantee the extraction of the most prominent or visible colors of the image and have several limitations, such as the extraction of multiple perceptually similar colors or inability to detect colors in smaller regions. Only a few studies have focused on extracting prominent colors from the image . Since the perception of prominent colors is a complex process that cannot be easily predicted with existing methods and low‐level image processing approaches, for example, color distribution or histogram analysis, the aim of our research is to develop a model for extracting image prominent colors based on machine learning.…”

“…Only a few studies have focused on extracting prominent colors from the image. 37 Since the perception of prominent colors is a complex process that cannot be easily predicted with existing methods and low-level image processing approaches, for example, color distribution or histogram analysis, the aim of our research is to develop a model for extracting image prominent colors based on machine learning. The model will be learned on real, human-extracted themes of prominent colors and use numerous features, which will be defined based on the aforementioned knowledge about HVS.…”