基于小波变换的图像融合技术研究

Study for Image Fusion Based on Wavelet Transform

摘要: 提出了一种基于小波变换的图像融合算法.首先,将配准后的多源图像进行小波分解,从而得到各个源图像的低频系数和高频系数.其次,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,通过小波逆变换得到融合图像.通过大量的实验以及与其他融合算法的比较分析,表明该方法的有效性和优越性.

Abstract: An algorithm of image fusion based on wavelet transform is proposed. Firstly, the obtained multi-source images which are registered are decomposed into several coefficients of low frequency and high frequency by using wavelet transform. Secondly, the wavelet coefficients of multi-source images are fused by different fusion rules based on regional features. Finally, the fusion image is obtained by inverse wavelet transform. Lots of experiments and comparisons with other fusion methods show that the effectiveness and superiority of image fusion method based on wavelet transform.