Title :
Texture synthesis based on wavelet transform
Author :
Wei Xiong ; Xuzhi Wang ; Liuchuang Gao
Author_Institution :
Sch. of Commun. & Inf. Eng., Shanghai Univ., Shanghai, China
Abstract :
Texture synthesis is an important process in image post-production. A Large number of previous approaches can be classified as either parametric or nonparametric method. Of these, the nonparametric approaches have achieved the most impressive results. This paper proposes a fast and efficient algorithm of texture synthesis algorithm; it is based on patch-based texture synthesis algorithm. We propose a pyramid-based synthesis algorithm. First, we apply wavelet to analysis texture figure. At the same time, we save the details of every level. And use the low-resolution to reconstruct the high-resolution texture by the inverse wavelet transform, and add the details to the results. In the paper, we will analysis some typical algorithm, and take an an experiment on it, then we will propose an improved algorithm and compare it with some typical algorithms.
Keywords :
image reconstruction; image resolution; image texture; inverse transforms; wavelet transforms; high-resolution texture reconstruction; image post-production; inverse wavelet transform; nonparametric method; patch-based texture synthesis algorithm; pyramid-based synthesis algorithm; Algorithm design and analysis; Educational institutions; Graphics; Image reconstruction; Wavelet analysis; Wavelet transforms;
Conference_Titel :
Audio, Language and Image Processing (ICALIP), 2012 International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4673-0173-2
DOI :
10.1109/ICALIP.2012.6376638