计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (13): 179-181.

• 图形、图像、模式识别 • 上一篇    下一篇

基于再生核滤波器的边缘保护图像插值方法

李 锌,张飞舟   

  1. 北京大学 遥感与地理信息系统研究所,北京 100871
  • 收稿日期:2007-08-21 修回日期:2007-11-19 出版日期:2008-05-01 发布日期:2008-05-01
  • 通讯作者: 李 锌

New edge preserving image interpolation based on reproducing kernel filter

LI Xin,ZHANG Fei-zhou   

  1. Institute of Remote Sensing and Geographic Information System,Peking University,Beijing 100871,China
  • Received:2007-08-21 Revised:2007-11-19 Online:2008-05-01 Published:2008-05-01
  • Contact: LI Xin

摘要: 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H2R)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。

关键词: 图像插值, 边缘保护, 再生核滤波器

Abstract: 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 H2R) 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 reducing jagged edges.

Key words: image interpolation, edge-preserving, reproducing kernel filter