摘要
为了兼得传统图像去噪算法的保边性与高效性的优点,本文根据图像空间相关性,设计了图像局部多项式逼近函数,理论上分析了局部逼近尺度,建立了局部多项式逼近去噪算法:首先对图像像素进行多项式拟合,构造局部多项式逼近函数;其次采用置信区间交集法则自适应选择局部多项式的逼近尺度;最后采用逼近算法对高斯噪声图像进行去噪.实验结果表明,本文算法继承了各向同性扩散的高效性和各向异性的保边性,同时弥补了各向异性扩散实时性较差的不足.
In order to have the advantages of edge protecting and high efficiency of traditional methods ofimage de-noising, according to the correlation of image＇ s space pixels, the paper has designed the localpolynomial approximation function, analyzed the local approximation theoretically and established the al-gorithm of local polynomial approximation （LPA）. For the noise image, first, made the polynomial fit-ting for the image pixel, structured the local polynomial approximation function. Second, used intersec-tion of confidence intervals （ICI） rule to select the ideal scale of the local polynomial adaptively. Finally,adopted the algorithm of LPA to de-noise the Gaussian noisy image. Experimental results show that thealgorithm inherits the traditional isotropic de-noising algorithm＇s advantage of high efficiency and makesup for the anisotropy de-noising algorithm＇s shortcomings that the computation time is too long, so itcan＇t meet the needs of the real-time requirement.
出处
《四川大学学报（自然科学版）》
CAS
CSCD
北大核心
2015年第5期1001-1006,共6页
Journal of Sichuan University(Natural Science Edition)
基金
四川省科技支撑项目(2013SF0157)
