光学4f系统灰度误差补偿的实现

为补偿光学4f系统灰度误差，提出基于直方图匹配和径向基函数(RBF)神经网络的灰度误差补偿方法。首先利用径向基函数神经网络拟合经光学4f系统输出图像的直方图与对应输入图像的直方图之间的非线性变换，得到输出图像与输入图像的直方图匹配变换曲线的最优估计；再依据直方图匹配曲线的最优估计对经光学4f系统的输出图像进行直方图匹配，得到灰度误差补偿后的图像。利用实际的光学4f系统进行光学实验，灰度误差补偿后图像的信噪比平均提高了2.96dB，视觉效果明显改善。实验结果表明，该方法能有效补偿光学4f系统灰度误差，提高基于光学4f系统的光学信息处理的精度。

Implementation of gray level error conpensation for optical 4f system

To compensate the gray level error in optical 4f system, a method for gray level error compensation based on histogram matching and Radial Basis Function (RBF) neural network was proposed. The nonlinear transformation of histogram between input and output images in optical 4f System was fitted by RBF neural network, then the optimal estimation of curve for histogram matching between input and output images was obtained. The gray level error compensation image was obtained by utilizing histogram matching according to the optimal estimation of curve for histogram matching. The average Peak Signal-to-Noise Ratio (PSNR) gain achieved was 2.96dB and the visual effect of images processed was improved by utilizing the proposed method in actual optical 4f system. The experimental results show the gray level error in optical 4f system can be compensated effectively and the precision of optical information processing was improved by the proposed method.