计算机科学与探索 ›› 2015, Vol. 9 ›› Issue (9): 1132-1138.DOI: 10.3778/j.issn.1673-9418.1409059

• 人工智能与模式识别 • 上一篇    下一篇

基于模糊算子的Tetrolet变换图像融合算法

沈  瑜1+,伍忠东1,王小鹏1,董亚楠1,江  娜2   

  1. 1. 兰州交通大学 电子与信息工程学院,兰州 730070
    2. 兰州交通大学 自动化与电气工程学院,兰州 730070
  • 出版日期:2015-09-01 发布日期:2015-12-11

Tetrolet Transform Images Fusion Algorithm Based on Fuzzy Operator

SHEN Yu1+, WU Zhongdong1, WANG Xiaopeng1, DONG Yanan1, JIANG Na2   

  1. 1. School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
    2. School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
  • Online:2015-09-01 Published:2015-12-11

摘要: 针对目前图像融合信息不完整,融合结果对比度不高的缺点,提出了一种基于模糊算子的Tetrolet变换图像融合算法。将源图像经过改进的Tetrolet变换,得到高频系数和低频系数;对于低通系数引入邻域能量及其接近度的融合规则,而对高频系数采用一种新的模糊融合算子,通过模糊推理确定各个源图像高频系数的权值,再对相应系数加权平均得到融合后的高频系数;对融合后的高频系数和低频系数,经Tetrolet反变换重构得到融合后的融合图像。通过实验证明了该算法的有效性。

关键词: 图像融合, Tetrolet变换, 模糊算子

Abstract: Aiming at the problems that the fused image information is incomplete and the contrast degree in the fused image is low, this paper proposes an improved Tetrolet transform images fusion algorithm based on fuzzy operator. Firstly, the images are converted to the high frequency coefficients and low frequency coefficients by the improved Tetrolet transform. For the low frequency coefficients, the neighborhood energy and proximity are introduced to the fusion rule. For the high frequency coefficients, a new kind of fuzzy fusion operator is adopted. According to local area features of high frequency coefficients in source images, the weights of corresponding coefficients are obtained through fuzzy reasoning. Then these coefficients are averaged to obtain the fused high frequency coefficients by the weights. Finally, the fused low frequency coefficients and high frequency coefficients are reconstructed by the inverse Tetrolet transform. The experimental results testify the algorithm validity on the images fusion.

Key words: multi-source images fusion, Tetrolet transform, fuzzy operator