摘要： 利用Wiener滤波或约束最小二乘方法复原的图像在图像灰度值发生跳变处会出现振铃式的波纹。受限制自适应图像复原算法对复原和平滑加以局部的适应性控制，有效地克服振铃波纹。在受限制自适应图像复原算法的基础上，通过提高加权数组的精细程度，改善复原的自适应控制能力，采用Neumann边界条件消除边界截断引起的寄生波纹。实验结果表明改进算法的复原效果较优。

关键词: 自适应图像复原, Sobel算子, Neumann边界条件

Abstract: The restored image which takes advantage of Wiener filter or least squares algorithm occur ringing waves in the place where the gray scale value of image is jumping. The constrained self-adaptive image restoration algorithm effectively overcomes the ringing waves through local adaptive control of restoration and smoothness. On the basis of the constrained self-adaptive image restoration algorithm, the ability of self-adaptive control of restoration is improved by increasing the precision of the weighted array, and the artifacts occurred by boundary truncation are removed by adopting Neumann boundary condition. Experimental results show that the improved algorithm gains better recovery effect.

Key words: self-adaptive image restoration, Sobel operator, Neumann boundary condition

中图分类号: 

• TP391.41