基于自适应开关插值算法的图像椒盐噪声滤波

Adaptive switching interpolation algorithm for filtering salt and pepper noise in image

针对传统中值滤波算法在滤除椒盐噪声时的缺点,提出了一种自适应开关插值算法。该方法根据椒盐噪声的特点,通过极大值、极小值和块均匀度检测来标志噪声,然后根据噪声分布情况,利用拉格朗日插值和自适应中值滤波来滤除噪声。实验结果表明,该方法对椒盐噪声密度为10%～80%的测试图像,能更加有效地抑制椒盐噪声并很好地保持了图像的细节信息,滤波性能比传统中值滤波方法更理想。该方法为图像去噪提供了一种新的途径。

According to shortcoming of conventional median filter algorithm in filtering salt and peper noise of image,the essay brought up a way of an adaptive switching interpolation filter.This method checked and identified noise through maximum-minimum and block uniformity,and then according to the distributed noise,filtered noise by using Lagrange interpolation and adaptive median filter.Experiment results on images with noise densities from 10% to 80% show that the proposed filter performs well in reducing salt and pepper noise and maintains a good image detail information.Therefore it has better filtering performance than the conventional median filter algorithm,and it provides a new way for image denoising.