欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对经典分形编码算法编码时间过长和基于K-均值聚类等快速分形编码算法依赖数据分布等问题,提出了一种基于免疫粒子群优化（IPSO）和核模糊聚类的快速分形图像编码算法.提出基于IPSO的核模糊聚类算法,将IPSO算法应用于聚类中心的求解中,并将其应用于分形图像编码,分别对子块和父块进行核模糊聚类,以更加合理的分类搜索取代全局搜索,减少编码时间.实验结果表明,新算法的编码时间约为经典分形编码算法的1/6,其峰值信噪比只略微下降;与基于K-均值聚类和基于粒子群优化聚类等快速分形图像编码算法相比,新算法能以更少的编码时间获得更高的峰值信噪比.
英文摘要：
Aiming at the lengthy of classical fractal coding algorithm and the problem of fast fractal image coding algorithm based on such as K-means clustering,a fast fractal image coding algorithm based on immunity particle swarm optimization（IPSO）and fuzzy kernel clustering is proposed.Firstly,an algorithm of fuzzy kernel clustering based on IPSO is presented.The IPSO algorithm is used to calculate the cluster centers.Then the proposed algorithm of fuzzy kernel clustering based on IPSO is applied to fractal image coding.The range blocks and domain blocks are clustered reasonably by fuzzy kernel method,respectively.Range blocks are searched in the corresponding category of domain blocks.As a result,the encoding time is reduced significantly.The experimental results show that,the encoding time of the proposed algorithm is about six times less than that of the classical algorithm at the cost of slight decrease of peak signal-to-noise ratio.Compared with the fast fractal image coding algorithm reported recently based on such as K-means clustering and particle-swarm-optimization clustering,the proposed algorithm can achieve higher peak signal-to-noise ratio in much less encoding time.
同期刊论文项目
同项目期刊论文
期刊信息
位置：