| 摘 要: 为了进一步提高传统导向滤波图像融合算法在图像处理过程中的效果，使得融合后的图像能够保留更多的细节信息，在传统的导向滤波图像融合法的基础上，利用非线性的Sigmoid函数可以映射到[0,1]的特性，用其代替原有线性的加权平均，最后得到融合后的图像。通过对实验结果进行对比分析发现，相较于传统的导向滤波图像融合算法，本文经过对权重重新分配后能够有效提高一些图像的融合效果。 |
| 关键词: 导向滤波；Sigmoid函数；图像融合 |
|
中图分类号: TP202
文献标识码: A
|
|
| Research on Improved Image Fusion Algorithm based on Guided Filtering |
|
GUO Wanling
|
(School of Science, Zhejiang Sci-Tech University, Hangzhou 310018, China)
Wl-guo@foxmail.com
|
| Abstract: In order to further improve the effect of the traditional guided filtering image fusion algorithm in the image processing process, the fused image can retain more details. Based on traditional guided filtering image fusion method, this paper proposes to replace the original linear weighted average with the non-linear Sigmoid function which can be mapped to the property between zero and one, and finally the fused image is obtained. The experimental results show that compared with the traditional guided filtering image fusion algorithm, the proposed algorithm can effectively improve the fusion effect of some images after redistributing the weights. |
| Keywords: guided filtering; Sigmoid function; image fusion |
