中文摘要：

针对当前阈值类算法在图像去噪的同时均会将原图像有用成分滤掉，破坏图像的完整性，处理后的图像模糊等问题，提出EMD.SG算法为图像去噪。依据EMD算法对图像的拆分，利用SG滤波器对每个采集点的邻域进行滤波。同时利用最小二乘法方法拟合出采集点邻域内最佳值，并结合IMF进行图像重构。该算法使图像处理过程良好地兼顾了图像除噪效果与图像信号完整性。实验结果表明此算法相比于其他算法具有优良的去噪能力。

英文摘要：

Since the current threshold algorithm may filter the useful components of the original image and destroy the imageintegrity while denosing the image,and the processed image is fuzzy,an EMD?SG algorithm is proposed to denoise the image.According to the EMD algorithm,the image is split,and the SG filter is used to filter the neighborhood of each collection point.The least square method is used to fit the best value inside the neighborhood of the acquisition points,and the image is recon?structed with IMF. This algorithm takes the image signal integrity and image denoising effect into account well in the image pro?cessing procedure. The experimental results show that,in comparison with other algorithms,this algorithm has excellent denois?ing ability.