基于小波变换与局部能量的多聚焦图像融合

本文提出了一种基于区域局部能量的不同聚焦点图像融合方法。本文利用小波分解，将图像分解为低频部分和高频部分，然后选择合适的比例，削弱低频部分，减小低频部分在整个图像能量中所占的比例，相对增大高频部分的比例，再重构图像。对于重构的图像，在空域中使用区域局部能量大小判定的方法，对各幅图像中的目标进行判断，并选择其中的清晰部分生成融合图像。该方法不但适用于多聚焦图像融合，而且还可以应用于特性类似的医学图像的融合。实验结果表明，该方法可以提取出多聚焦图像中的清晰目标，生成的融合图像效果优于Laplacian塔型方法和小波变换方法。

Multi-Focus Image Fusion Based on Wavelet Transform and Local Energy

A new multi-focus image fusion algorithm is given in this paper, which is based on the difference of the re- gion energy of each image. The wavelet decomposition is used to decompose the original image to two different parts, namely, the low frequency part and the high frequency part. The high frequency part contains the horizontal high fre- quency, the vertical high frequency and the diagonal high frequency. For the low frequency part, an approprlate pa- rameter R is chosen to reduce the proportion of the energy of the low frequency part to that of the whole image. In this way, the proportion of high frequency part to the low frequency part is improved. The adjusted images are recon- structed with wavelet reverse transform. For the new reconstructed images, the method of comparing the region en- ergy to determine in which image the object is clear is used. The clear object is decided by the comparison of the dif- ference of energy of the two new adjusted different focus images pixel by pixel. Through this way, the clear region of each original image are decided automatically, and merged into the fused image. The approach can be applied not only to multi-focus image fusion, but also to image fusion of medical images. with a similar property of multi-focus im- ages. Experiments show that the proposed algorithm works better in extracting the clear object from the original im- ages than that of the other image fusion methods in multi-focus image fusion.