基于小波变换的多模态图像融合算法的改进

Improved multi-modal image fusion method based on wavelet transform

为了进一步提高医学图像的融合效果,研究和改进了基于小波变换的图像融合算法,提出了一种改进小波变换金字塔融合算法。该算法对经过多层小波变换后的高低频小波系数,分别使用局部均值加权和分层线性加权的小波系数融合规则进行融合。通过编程试验,将该算法与空域和频域的各种融合算法进行对比,并使用主观和客观两种评价方法进行综合评价。实验结果表明,针对灰度图像特别是医学图像的融合,提出的融合算法与文中的对比算法相比较,在主观和客观的综合评价上表现出更好的融合效果。

In order to further enhanee the effeet ofmedicine image fusion, the fusion algorithm based on wavelet transformation is studied and improved. The improvement the pyramid fusion algorithm based on wavelet transformation is proposed, this algorithm after the process multi-layer wavelet transformation separately uses the wavelet coefficient fusion rules of partial average value weighting and lamination linear weighting in the fusion ofhigh and low fi＇equency wavelet coefficient. Through the programming experiment, this algorithm compared with a variety of spatial-domain and frequency-domain fusion algorithm, and using two kinds of subjective and objective evaluation method conducted a comprehensive evaluation of fusion results. Experimental results show that compared with the comparison algorithm, the proposed fusion algorithm has a better results.