计算机工程与应用 ›› 2012, Vol. 48 ›› Issue (33): 203-206.

• 图形、图像、模式识别 • 上一篇    下一篇

一种新的基于NSCT域的遥感图像增强算法

李殿均1,贾振红1,覃锡忠1,杨  杰2,胡英杰3,杜超本1   

  1. 1.新疆大学 信息科学与工程学院,乌鲁木齐 830046
    2.上海交通大学 图像处理与模式识别研究所,上海 200240
    3.新西兰奥克兰理工大学 知识工程与发现研究所,新西兰 奥克兰 1020
  • 出版日期:2012-11-21 发布日期:2012-11-20

New NSCT-based remote sensing image enhancement algorithm

LI Dianjun1, JIA Zhenhong1, QIN Xizhong1, YANG Jie2, HU Yingjie3, DU Chaoben1   

  1. 1.College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China
    2.Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai 200240, China
    3.Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland 1020, New Zealand
  • Online:2012-11-21 Published:2012-11-20

摘要: 针对图像增强处理中产生的伪Gibbs现象、清晰度差等问题,利用下采样轮廓波变换(NSCT)的平移不变性特点,来抑制伪Gibbs现象,同时把模糊对比度和空间频率相结合来处理NSCT系数,提高了增强后图像的清晰度。实验结果证实,该算法使得增强后图像的质量明显优于常用的增强算法,具有一定实践价值。

关键词: 图像增强, 非下采样Contourlet变换(NSCT), 模糊对比度, 空间频率

Abstract: In order to solve the problem appearing in the process of image enhancement, such as, pseudo-Gibbs phenomenon and low contrast, a new threshold algorithm is proposed which is on the basis of NSCT domain. On the one hand, this proposed algorithm makes use of NSCT’s shift-invariance to prohibit the pseudo-Gibbs phenomenon, on the other hand, deals with NSCT’s coefficient by combining fuzzy contrast and spatial frequency to improve contrast and get better visual effect. The experimental results show that the proposed algorithm gets better results than the traditional method and owns some certain value in practical application.

Key words: image enhancement, Nonsubsampled Contourlet Transform(NSCT), fuzzy contrast, spatial frequency