01984nas a2200337   4500000000100000000000100001008004100002260002000043653002100063653002300084653001000107653003400117653001600151653003500167653001200202653002900214653002100243653002300264653002200287653002000309100001500329700001800344700001600362700001800378245008000396856015300476300001200629490001500641520094800656020004201604       2018                            d  bSpringer Verlag10aTextile printing10aImage segmentation10aColor10aRendering (computer graphics)10aImage-based10aImage-based artistic rendering10aNeedles10aRandom-needle embroidery10aStitch selection10aColor quantization10aImage compression10aSparse modeling1 aKewei Yang1 aZhengxing Sun1 aShuang Wang1 aHui-Hsia Chen00aImage Stylization for Thread Art via Color Quantization and Sparse Modeling  uhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85047467133&doi=10.1007%2f978-3-319-77380-3_49&partnerID=40&md5=26b34b6dcd3922d8aea22a91ced54a6e  a515-5250 v10735 LNCS3 aWe present an image stylization method to simulate a graceful Chinese art—Random-needle Embroidery designated as Intangible Cultural Heritage. We first develop an effective way to simulate a single thread, and define rendering primitive called stitch which is a collection of threads arranged in a certain pattern. Then, we segment the input image and partition each region into non-uniform sub-regions, from which a color quantization method is proposed to select colors used in the rendering process for each sub-region from a specific color library. During runtime, new stitches can be synthesized for each sub-region via sparse modeling based on the pre-defined stitches. Smoothness constraints are added to this process to avoid local distortions. Finally, rendering image is generated by placing stitches with different attributes on the canvas. Experiments show that our method can perform fine images with the style of random-needle.  a03029743 (ISSN); 9783319773797 (ISBN)