多分辨率图像插值

IMAGE INTERPOLATION BASED ON MULTIRESOLUTION MODEL

提出了一种结合小波和分形的混合图像插值算法。与图像处理中的传统插值算法比较，该算法通过提取图像的分形特征保持图像的全局相关性，更好地保持图像的细节信息，避免了传统插值算法引起的锯齿效应和平滑效应。实验证明该方法可以比传统的插值算法取得更高的信噪比。

In this paper, a hybrid approach of image interpolation combining the wavelet with fractal is proposed. Compared with the traditional methods used in the image processing, this approach offers advantages of taking into account the correlation of the whole image, keeping fine details of image and avoiding the sawtooth effect and smoothing effect associated with traditional image interpolation techniques. The experimental results show that our approach is able to get higher PSNR than existing interpolation methods in most cases.