J4 ›› 2012, Vol. 39 ›› Issue (1): 34-37+85.doi: 10.3969/j.issn.1001-2400.2012.01.007

• 研究论文 • 上一篇    下一篇

一种新的NSCT超分辨率图像复原技术

杨贞萍;牛海军;丁磊   

  1. (西安电子科技大学 计算机学院,陕西 西安  710071)
  • 收稿日期:2011-06-28 出版日期:2012-02-20 发布日期:2012-04-06
  • 通讯作者: 杨贞萍
  • 作者简介:杨贞萍(1987-),女,西安电子科技大学硕士研究生,E-mail: endless-joy0213@163.com.
  • 基金资助:

    国家部委基金资助项目(513160702)

New image super-resolution restoration method by NSCT

YANG Zhenping;NIU Haijun;DING Lei   

  1. (School of Computer Science and Technology, Xidian Univ., Xi'an  710071, China)
  • Received:2011-06-28 Online:2012-02-20 Published:2012-04-06
  • Contact: YANG Zhenping

摘要:

考虑到非下采样Contourlet变换具有多尺度性和多方向性,提出了一种基于非下采样Contourlet变换的图像复原算法.首先对给出的序列低分辨率图像进行图像配准,对配准图像进行非下采样Contourlet变换,分解成低频及高频部分,对低频和高频分别采取不同的融合策略进行融合,再对融合后的高频和低频进行非下采样Contourlet变换逆变换得到融合图像.对融合后的图像再进行非下采样Contourlet变换,分别对高频细节和低频进行插值,再经非下采样Contourlet逆变换复原成高分辨率的图像.实验表明,该算法在主观效果和客观评价上均优于传统复原算法,是一种可行的图像复原新算法.

关键词: 图像配准, 图像融合, 非下采样Contourlet变换, 插值

Abstract:

Based on the multi-scaled and multi-directional properties of Nonsubsampled Contourlet Transform (NSCT), an image super-resolution restoration algorithm is proposed. The algorithm includes image registration and image restoration. First sub-pixel image registration is applied. Then a fused image can be obtained from the registered images by performing NSCT and the inverse NSCT. After the low frequency and high frequency of the fused image are interpolated, a high-resolution image can be obtained by performing the inverse NSCT. Experimental results show that the proposed algorithm outperforms the traditional algorithms in terms of both visual quality and objective evaluation criteria.

Key words: image registration, image fusion, nonsubsampled contourlet transform, interpolation

中图分类号: 

  • TP391