Automatic thread painting generation

DOI10.4310/CIS.2016.V16.N4.A3zbMATH Open1393.94105arXiv1802.04706MaRDI QIDQ1659042FDOQ1659042

Authors: Xiaonan Fang, Bin Liu, Ariel Shamir 

Publication date: 15 August 2018

Published in: Communications in Information and Systems (Search for Journal in Brave)

Abstract: ThreadTone is an NPR representation of an input image by half-toning using threads on a circle. Current approaches to create ThreadTone paintings greedily draw the chords on the circle. We introduce the concept of chord space, and design a new algorithm to improve the quality of the thread painting. We use an optimization process that estimates the fitness of every chord in the chord space, and an error-diffusion based sampling process that selects a moderate number of chords to produce the output painting. We used an image similarity measure to evaluate the quality of our thread painting and also conducted a user study. Our approach can produce high quality results on portraits, sketches as well as cartoon pictures.

Full work available at URL: https://arxiv.org/abs/1802.04706

Recommendations

• Example based painting generation
• Probabilistic color-by-numbers, suggesting pattern colorizations using factor graphs
• The synthesis of Chinese fine-brushwork painting for flower
• On fine art and generative line drawings
• scientific article; zbMATH DE number 1849124

zbMATH Keywords

chord spacechords on the circleerror-diffusion based sampling processNPR representation of an input imagethread painting generationthreads on a circle

Mathematics Subject Classification ID

Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10)

This page was built for publication: Automatic thread painting generation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1659042)