基于区域特征的小波变换图像融合方法

图像融合的目的是把来自多传感器的数据互补信息合并成一幅新的图像，以改善图像的视觉效果。笔者提出一种基于小波变换的图像融合方法，其思想是先把待融合图像采用小波进行分解，然后在对分解后的小波系数矩阵采用区域特征进行融合处理，最后采用小波逆变换得到融合图像。该方法很好地区分了图像低频分量和高频分量对融合的不同影响，实验表明取得了较好的融合效果。

Wavelet Transform Image Fusion Based on Regional Features

The purpose of image fusion is to merge complementary information from multi sensor data for visual perception so as to improve the visual perception of the image. A wavelet transform image fusion based on regional features is proposed. Firstly, it decomposed the original images into four sub images via WT. Secondly, it calculated the regional features of each sub image and chose the different rule of fusion based on regional features. Finally, the whole fusion image can be obtained by inverse wavelet transform. The experiment results showed that the proposed method seemed better.