基于再生核滤波器的边缘保护图像插值方法

New edge preserving image interpolation based on reproducing kernel filter

图像插值是数字图像处理中的一个关键问题,提出一种基于再生核的滤波器的图像插值方法。在H(2R)空间中,可以构造出再生核滤波器并推出插值公式。根据范数理论,再生核滤波器具有良好的逼近效果。实验结果表明:该算法能够克服其它算法的缺点,获取的高分辨率图像既能够保持图像的边界信息,又能保证图像的光滑性。

Image interpolation is one of the key technologies in image/video processing.In this paper,we propose a novel approach to interpolate image using reproducing kernel filter （RKF）.The proposed image-interpolating method is performed in the Hilbert space H^2（R） and has the advantage of offering good approximation of the function values and its first and second derivatives at the knots.Through comparisons with other algorithms it is shown that the new interpolation produce higher quality, but visually it is very efficient at reducinng jagged edges.