Multilayered stitch generating for random-needle embroidery

• Published in: The Visual computer Vol. 38; no. 11; pp. 3667 - 3679
• Main Authors: Ma, Chen, Sun, Zhengxing
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2022; Springer Nature B.V
• Subjects: Artificial Intelligence; Artists; Color imagery; Computer Graphics; Computer Science; Image Processing and Computer Vision; Methods; Needlework; Original Article; Seeds; Segments; Stitches; Texture; Non-photorealistic rendering; Local texture growth; Stitch modeling; Color dithering
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-021-02195-2

Random-needle embroidery is a kind of traditional Chinese embroidery where artists reproduce the original color image using multilayered intersecting stitches and overlapped deliberately. In other words, artists embroider intersecting stitches layer by layer to depict true color subjects. To create this embroidery art, the major challenge lies on evenly distribution of intersecting stitches to prevent the canvas in embroidery areas from being exposed. Meanwhile, intersecting stitches in each layer should be distributed as evenly as possible so that each layer of intersecting stitch can be quantified as a segment color to synthesize the target segment color. To tackle these challenges, we introduce local texture growth mechanism from example-based discrete element texture synthesis to the application of random-needle embroidery art stylization and propose a new local growth where a uniformity metric is designed to keep intersecting stitches nearly evenly distributed in each layer. In addition, we adopt a color dithering model to specify a color for each layer of monochromatic intersecting stitches at microscopic scale. We apply our method on a rich variety of images, and visually appealing random-needle embroidery images can be obtained in all cases.