A comparative study was made on the parameters of the local characteristics of image clarity, and the optimal parameter of the Energy Of Laplacian ( KOI.) was obtained. A new intelligent image fusion algorithm based on EOL was proposed. A set of registered images was firstly segmented, and then local EOIs of segmented image blocks were computed. EOLs were input into neural network and the target vectors were automatically obtained by comparing values of EOLs. Test images were segmented and their EOIs were put into trained network and the rough fusion images were generated. Final fusion results would be obtained by consistence verification. The experimental results demonstrate the good fusion performance on different source images.%对衡量图像清晰程度的局部特征参数进行了对比研究,得出了拉普拉斯能量(EOL)最优参数.提出一种使用拉普拉斯局部特征的智能化图像融合算法.算法首先对已配准的图像集进行分割,对分割图像分块并计算EOL,将EOL作为网络输入进行训练,根据EOL比对自动决定训练的目标向量.将测试图像进行分割并计算局部EOL,将EOL作为测试输入进行粗融合,最后进行一致性校验得到最终融合结果.实验研究表明,本算法对不同传感器的图像均取得了良好的融合效果.
展开▼
