首页 | 本学科首页   官方微博 | 高级检索  
     

应用PSO的快速纹理合成算法
引用本文:张岩,李文辉,孟宇,庞云阶.应用PSO的快速纹理合成算法[J].计算机研究与发展,2005,42(3):424-430.
作者姓名:张岩  李文辉  孟宇  庞云阶
作者单位:吉林大学计算机科学与技术学院,长春,130012
基金项目:国家自然科学基金项目(69883004) 国家博士点基金项目(20010183041)
摘    要:应用PSO的快速纹理合成算法是一种高效的纹理合成算法,应用粒子群优化(PSO)算法对基于块采样的纹理合成算法的搜索匹配过程进行了改进,改变了原算法的全遍历搜索过程,在不影响合成质量的前提下加快了合成速度.本算法对于按序和随机的各种应用都能在一台中等的PC机上几秒内合成高质量的纹理.并对算法执行中的粒子数、迭代次数对合成速度和合成效果的影响进行了详细的分析.

关 键 词:纹理合成  基于块采样  粒子群优化(PSO)

Fast Texture Synthesis Algorithm Using PSO
Zhang Yan,Li Wenhui,Meng Yu,Pang Yunjie.Fast Texture Synthesis Algorithm Using PSO[J].Journal of Computer Research and Development,2005,42(3):424-430.
Authors:Zhang Yan  Li Wenhui  Meng Yu  Pang Yunjie
Abstract:Texture synthesis is of importance to computer vision and graphics. The technique has great potential in many applications, especially in image editing, computer animation, real-time rendering for large scale of scenes, realistic and non-photorealisitic rendering etc.. In this paper, a survey of traditional and contemporary texture synthesis methods is presented. Fast texture synthesis algorithm using PSO is an effective texture synthesis algorithm. Particle swarm optimization (PSO) is applied to improve the process of searching and matching in the texture synthesis by patch-based sampling, thus changing the throughout search method of the original algorithm and speeding up the process of synthesis without influencing the quality of the image. It is shown that high-quality texture can be synthesized in several seconds on a midlevel PC, and this algorithm works well for a wide variety of texture ranging from regular to stochastic. How the number of the particles and the iterations influence the speed of the synthesis is analyzed in detail.
Keywords:texture synthesis  patch-based sampling  particle swarm optimization (PSO)
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号