参考曲率的双线性插值滤波

Bilinear interpolation filtering algorithm based on curvature

为了在滤除椒盐噪声的同时尽可能地保留图像细节,提出了一种基于曲率的双线性插值滤波算法。该算法鉴于双线性插值的低通滤波固有特性,引入像素值的变化以构造类双线性插值模型;为了获得相邻像素的方向趋势,引入曲率信息;以曲率信息为参考,选择最接近原始图像变化规律的方向进行双线性插值滤波。实验结果表明,该方法在滤除噪声的同时有效地保留了图像的细节,且滤波效果优于传统的滤波算法。

In order to filter out salt and pepper noise while preserving image detail as possible, it proposes a bilinear interpolation filtering algorithm based on curvature. In view of the inherent characteristics of the bilinear interpolation of the low-pass filter, it introduces the changes of pixel values to construct the class of bilinear interpolation model. The curvature information is used to get the direction trend of adjacent pixels. It selects the direction which is closest to the original image variation to filter image using bilinear interpolation based on the curvature information. Experimental results show that this method can filter out the noise while maximizing the retention of details of images, and filtering results are better than traditional filtering algorithms.