自适应Catmull-Rom样条图像放大

摘要

Based on a geometric classification, a new image amplification method using adaptive Catmull-Rom interpolation is presented in this paper. Compared to the traditional image reconstruction method using Catmull-Rom interpolation, the proposed method can preserve geometric features well. First, the geometric edges of the original image are classified. Then for the edge pixels in the original image, the tangential direction and tangential length of the Catmull-Rom spline are adjusted accordingly. The experimental results show the feasibility of the method in which the edges in the target image are well preserved.%针对Catmull-Rom样条图像插值放大不能保证图像内各物体之间边界清晰的问题,提出一种基于几何分类的自适应Catmull-Rom样条图像插值放大算法.通过对原图像的边缘进行几何分类,根据原图像的边缘几何类型插值目标图像中的未知像素点；若未知像素点为原图像中的边缘,则调整Catmull-Rom样条的切向方向和切向长度来计算未知像素值,得到边缘保持的目标图像.实验结果表明,应用该算法得到的目标图像边界清晰、细节模糊减少,忠实地反映了原图像的面貌.