Title :
A new method of texture synthesis based on gradient structure information searches along a spiral path
Author :
Yong-qian Tan ; Yuan-yuan Pu ; Wen-hua Qian ; Dan Xu
Author_Institution :
Sch. of Inf. Sci. & Eng., Yunnan Univ., Kunming, China
Abstract :
Most of the existing texture synthesis algorithms were proposed in the pursuit of the better synthesis quality or quick synthesis speed, but they could not satisfy requirements at the same time. In this paper, a new texture synthesis algorithm is presented. It adopts the color and the gradient as the similarity measurement of between the two matching patch, which improves their similarity extent. Moreover, a spiral-path searching method is used to search the best texture matching patches and the synthesis time can be decreased dramatically. The experiment results show that not only the synthesis speed is rapider t in great degree, but also the synthesis quality is improved.
Keywords :
image matching; image texture; gradient structure information; quick synthesis speed; similarity measurement; spiral path searching method; synthesis quality; synthesis time; texture matching patches; texture synthesis algorithm; Automation; Educational institutions; Image color analysis; Information science; Intelligent control; Spirals; Surface texture; gradient structure information; matching patch; spiral path searching; texture synthesis;
Conference_Titel :
Intelligent Control and Automation (WCICA), 2012 10th World Congress on
Conference_Location :
Beijing
Print_ISBN :
978-1-4673-1397-1
DOI :
10.1109/WCICA.2012.6359412