Karhunen-Loeve transform ( KLT) is optimum of variance distribution in all orthogonal transformation. 卡&洛变换(KLT)是所有正交变换中方差分布最佳者。
In this paper, some theories and methods of compression of multispectral images are reviewed and researches on multispectral remote-sensing image compression by Karhunen-Loeve Transformation ( KLT) and neural network are discussed. 本文在对一些目前已有的多光谱图像压缩方法进行深入研究的基础上,分别利用K-L变换和神经网络的方法实现了遥感图像的压缩。