整数解SA优化迭代维纳滤波的图像复原

Iterative Wiener Filters Optimized by Integer Solution SA for Image Restoration

针对盲或非盲图像复原的问题,基于图像复原的实际情况,结合整数解模拟退火(SA)算法,以向量矩阵形式线性退化模型的约束条件作为优化目标,利用经过维纳滤波的信号作为原始图像方差估计的更新,提出整数解模拟退火优化迭代维纳滤波的图像复原算法。通过不同类型的模糊图像复原进行仿真及验证,结果表明,所提方法能保证收敛性和稳定性,适用于盲或非盲图像复原,效果良好。

In view of the blind or non-blind image restoration problem,based on the actual situation of image restoration, combined with simulated annealing algorithm whose solution is the integer,taking the constraint condition of the vector and matrix form of the linear degraded model as the optimization goal,using the Wiener filtered signal as an improved prototype to update the covariance estimates,the iterative Wiener filter by applying the integer solution simulated annealing optimization algorithm is proposed to restore the fuzzy images.