通过对航天光学遥感器MTF模型和遥感图片的分析，从图像中提取出与MTF有关的特征信息，采用人工神经网络(ANN)作为工具，将这些特征信息作为ANN的输入向量。在对大量MTF已知的遥感图片进行训练后，ANN可以对未知的遥感图片进行MTF测试。这种方法被称为MTF的一元评价方法，即通过对遥感器传输下来的任意一幅地面景物图像进行MTF的在轨评价，无需在地面铺设特定形状靶标或已知的参考图片。实验结果表明，平均评价误差约为5%，具有很强的抗噪声能力。

Through analyzing the modulation transfer function (MTF) of the space optical remote sensor (SORS) and remote images,the eigenvectors related to MTF in the image are abstracted and used as the input of artificial neural network (ANN). After being arained by a great lot of images that MTF are known,the ANN can assess the MTF of totally unknown images. This method is called univariate assessment,namely,this method can assess the MTF of SORS through images of any landscape,and needn't the special views on the ground or reference images. The experiment results show that the mean assessment errors are approximately 5%,and this method is effective even if high noise is added to the images.