包络滤波算法及其在图像去噪中的应用

Envelope filtering algorithm and its application in image denoising

针对图像处理中的图像去噪问题,研究和提出了一种基于包络线的包络滤波方法。该方法通过对包络线进行修正并进行均值,得到原始信号的一种逼近,这种逼近能够有效地保持信号的主要波形成分和边沿,同时抑制信号中的低幅度噪声扰动,从而达到滤除噪声保持边沿的目的。将这一算法应用于图像去噪可以很好地去除低幅度噪声,并保持图像的轮廓与边缘,结果大大优于加权平均、中值滤波和小波去噪技术。

A new filtering algorithm for image denoising is proposed, which is based on the modified envelopes. This algorithm modifies the signal＇s envelopes and takes corresponding average, and then obtains the approximation of the original signal as the filtered signal. While smoothing the small amplitude noise, the approximation can maintain the primary ingredient and edge of the signal effectively. When the algorithm is applied into image denoising, low range noise can be eliminated in effect, and at the same time the image＇s main profile and edge are kept effectually. The result of the experiments shows that the new algorithm performs better than the other methods of mean filtering, median filtering and wavelet denoising.