光学学报, 2007, 27 (3): 424, 网络出版: 2007-03-15
基于高斯函数假设的图像频谱恢复特性分析方法
A Method for Image Spectrum Restoration Property Analysis Based on Gaussian Function
图像处理 图像复原算法 分析方法 频谱恢复特性 高斯函数 方差比 image processing image restoration algorithm analysis method spectrum restoration property Gaussian function variance ratio
摘要
为了对图像复原算法频谱恢复特性进行分析和评价, 提出了一种基于高斯函数假设的分析新方法。该方法假设光学传递函数H和退化图像频谱函数G为高斯函数, 采用方差以及提出的方差比作为频谱宽度指标, 对图像复原算法的频谱恢复特性进行定量分析和评价。分析中对H和G曲线设定两组方差, 分无噪声和有噪声两种情况, 计算出约束最小平方滤波法(CLS)和最大似然法(PML)等图像复原算法复原的图像频谱曲线及其方差和方差比, 采用计算结果对复原算法进行定量的分析和评价, 获得良好的效果。分析指出, 最大似然法的频谱外推能力和噪声抑制特性均明显好于约束最小平方滤波法。对两种算法的分析评价实验表明, 高斯函数假设分析方法是一种简便有效的图像频谱恢复特性分析方法。
Abstract
In order to analyze and evaluate the spectrum restoration property of image restoration algorithms, a new method based on Gaussian function is proposed. The optical transfer function H and degraded image spectrum function G are assumed as Gaussian functions, and the variance and variance ratio are used as indexes of the spectrum width to analyze and evaluate the spectrum restoration property of the image restoration algorithms quantificationally. The curves of H and G are enacted in two groups of different variances, and the variance and variance ratio of the image spectrum restored by constrained least squares restoration (CLS) and maximum likelihood estimation (PML) are calculated in no-noise and with-noise cases in analysis. The two algorithms are analyzed and evaluated by the calculation results, and the analysis proves that PML is better than CLS in spectrum extrapolation and noise restraint. The experimental results show that the method is easy and effective.
陈华, 李陶深, 赵进创. 基于高斯函数假设的图像频谱恢复特性分析方法[J]. 光学学报, 2007, 27(3): 424. 陈华, 李陶深, 赵进创. A Method for Image Spectrum Restoration Property Analysis Based on Gaussian Function[J]. Acta Optica Sinica, 2007, 27(3): 424.