基于多尺度对比度塔的图像融合方法及性能评价

给出了一种新的基于对比度塔形分解的分层图像融合方法，其基本思想是先对源图像进行对比度塔形分解，其次，按照融合规则，采用基于区域特性量测的加权算子去构造融合图像对应的对比度金字塔，最后，通过逆塔形变换重构融合图像。该方法被成功地用于图像的融合处理，此外，利用熵，交叉熵，互信息，均方根误差，峰值信噪比等参量，对该融合方法的融合性能进行了评价与分析，实验结果表明，该融合方法是十分有效的。

A Multiscale Contrast-Pyramid-Based Image Fusion Scheme and Its Performance Evaluation

A novel hierarchical image fusion scheme based on contrast pyramid decomposition is presented. The basic idea is that: first to perform a contrast pyramid decomposition of each source image, and then the contrast pyramid of the fused image is constructed by using region based weighted operators according to different fusion rules, finally the fused image is obtained by taking inverse pyramid transform. This approach has been successfully used in image fusion. In addition, with the use of the parameters such as entropy, cross entropy, mutual information, root mean square error and peak to peak signal to noise ratio, the performance of the fusion scheme is evaluated and analyzed. The experimental results show that the fusion scheme is effective.