Title :
Fast texture transfer through the use of wavelet-based image fusion
Author_Institution :
Massachusetts Inst. of Technol., Cambridge
Abstract :
This paper describes a new texture transfer scheme based on wavelet image fusion. Texture transfer applies the pattern of the texture image to the source image. While most of the current state-of-the-art methods perform texture transfer in space domain, the scheme introduced in this paper processes images using image fusion in wavelet domain. Image fusion is a popular method to process information from multiple images and combine the images into a smaller number of images. In the application to texture transfer, the approximation of the source image is extracted and used for the synthesized image. In addition, edges of the source and texture images are extracted and preserved in the synthesized image. This is done through the use of 2- D wavelet decomposition. Comparison to the current state- of-the-art methods is provided in the paper. It is concluded that wavelet-based texture transfer performs a reasonable texture transfer, and it is relatively fast.
Keywords :
edge detection; image fusion; image texture; wavelet transforms; 2D wavelet decomposition; edge extraction; edge preservation; source image approximation; texture transfer scheme; wavelet-based image fusion; Computer science; Image analysis; Image fusion; Image texture analysis; Notice of Violation; Pattern analysis; Pattern recognition; USA Councils; Wavelet analysis; Texture transfer; image fusion; information fusion; wavelet image processing;
Conference_Titel :
Wavelet Analysis and Pattern Recognition, 2007. ICWAPR '07. International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-1065-1
Electronic_ISBN :
978-1-4244-1066-8
DOI :
10.1109/ICWAPR.2007.4420677