应用相关系数的小波变换图像融合算法

多聚焦图像融合的关键问题是如何保持原始图像的边缘和细节信息,由此本文提出了一种基于相关系数的小波变换图像融合策略.针对小波分解的不同频率域,设计了两种选择高频系数和低频系数的原则.选择高频系数时,采用绝对值最大、平均与选择相结合两个原则；选择低频系数时,基于平均与选择相结合、相关系数两个原则.最后将提出的算法用于多聚焦...

A Wavelet Transform Image Fusion Algorithm Based on Related Coefficients

The key problem in multi-focus image fusion is how to keep the detail and edge in the original image.Therefore,a new image fusion algorithm is developed based on the related coefficients of wavelet transform.The schemes of choosing high frequency and low frequency coefficients are two approaches designed. While choosing high frequency coefficients,we select these that have the maximal absolute values and combination of averages with selection.When choosing low frequency coefficients,we select two principles based combination of average with selection and coefficients related.The algorithm is used to fuse two multi-focused images. In addition, the performance of the fusion methods is appraised and analysed with objective evaluation index. The experiments show that this algorithm can preserve all the useful information from the primitive images and all the targets in the fused image are very clear. Each fusion evaluation index achieves improvement. The algorithm is of certain effective and parctial.