Title :
Particle swarm optimization-based texture synthesis and texture transfer
Author :
Zhang, Yan ; Meng, W. ; Li, Wen-Wi ; Pang, Yunjie ; Hong-Peng Wang
Author_Institution :
Coll. of Comput. Sci. & Technol., Jilin Univ., Changchun, China
Abstract :
In this paper, a fast texture synthesis algorithm-swarm intelligence-based texture synthesis is presented. The algorithm uses an intelligent particle swarm optimization (PSO) algorithm to search the best matching patch from the input sample textures and paste it onto the output texture. After a series of experiments, it is proved that the algorithm is effective to a variety of textures, and high quality textures can be synthesized with a mid-level PC in real-time by using it. Furthermore, we extend it to an application-texture transfer.
Keywords :
Markov processes; evolutionary computation; feature extraction; image matching; image resolution; image texture; optimisation; random processes; Markov processes; fast texture synthesis algorithm; feature extraction; intelligent particle swarm optimization algorithm; random processes; swarm intelligence based texture synthesis; texture transfer algorithm; Clouds; Computer graphics; Computer science; Computer vision; Image generation; Layout; Particle swarm optimization; Pixel; Sea surface; Surface texture;
Conference_Titel :
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on
Print_ISBN :
0-7803-8403-2
DOI :
10.1109/ICMLC.2004.1384545