基于散斑图像梯度域的数字图像相关盲去模糊方法

DIGITAL IMAGE CORRELATION BLIND DEBLURRING METHOD BASED ON SPECKLE IMAGE GRADIENT

针对复杂测量环境或高动态测量过程中出现的运动模糊问题,提出了一种灰度稀疏先验与参考图像梯度域先验相结合的散斑图像盲去模糊方法。该方法以灰度直方图峰值的L 0范数与参考图像梯度域分布建立优化函数正则项,使用二次分裂方法估计清晰图像,再以交替迭代的方式进行卷积核细化。在模糊核估计完成后,使用Richardson-Lucy非盲去卷积方法完成散斑图像的复原。实验结果证明:所提出的散斑图像盲去模糊方法与针对自然图像与文本图像的经典方法相比,获得了更优的图像去模糊效果,并提高了数字图像相关测量精度与鲁棒性。

Aiming at the problem of motion blur in complex measurement environment or high dynamic measurement,a blind deblurring method for speckle image based on the combination of gray sparsity prior and reference image gradient prior is proposed.This method takes the norm of the peak value of the gray histogram and the gradient of the reference image as the regular terms,uses the quadratic splitting method to estimate the clear image,and evaluates the convolution kernel in an alternating iterative way.After the fuzzy kernel estimation is completed,the Richardson-Lucy non-blind deconvolution method is used to restore the speckle image.Experimental results show that compared with the classical method for natural image and text image,the proposed method achieves better image deblurring results and improves the accuracy and robustness of digital image correlation measurement.