基于神经网络的光学4f系统图像复原

Image Restoration of 4f Optical System Based on Neural Network

由于光学4f系统存在诸多误差因素,引起所采集到的图像存在大量的噪声。探讨了基于神经网络的图像复原的一般方法,结合4f光学系统的特点,提出采用整体图像处理的复原思路,有效地利用了系统误差的结构信息。实验结果表明,该方法对光学4f系统的图像复原具有较好的效果。

Since there are many errors in an optical 4f system, the recorded images contain a large number of noises. This article discusses the general image restoration method based on neural network, combined with the characteristics of optical 4f system, a restoration method based on whole image is proposed, which takes effective use of the structure of the system error information. The result shows that the new method is effective in image restoration of 4f optical system.