改进的Wiener滤波在图像恢复中的应用

Application of Improved Wiener Filter in Image Restoration

在Wiener滤波进行图像恢复时,利用遗传算法(GA,Genetic Algorithm)全局和局部搜索力强的优势,搜索Wiener滤波的信噪比最优Γ。为了得到最优Γ值,利用峰值信噪比(PSNR,Peak Signal-to-Noise Ratio)作为图像恢复质量评价指标,对经过处理的LIVE数据库图像、IKONOS、ZY-3卫星图像进行实验。结果表明:无论图像噪声大小,该方法都可以找到Wiener滤波的最优Γ值。

In this paper, an optimization technique using the Genetic Algorithm is proposed to find the optimal value of the ratio ,which is a priori knowledge of the signal-to-noise ratio,in the application of Wiener filter to image restoration. The proposed method is suitable and effective for control experiment in conjunction with PSNR （Peak Signal-to-Noise Ratio） image-quality-assessment measure in order to obtain the optimal for the measure. Experiment,which is based on processing of Lena image from LIVE database. IKONOS image. ZY-3 image, has shown that with this method the optimal can be found regardless of degree of noise degradation.