基于耦合偏微分方程的煤矿图像去噪算法

Denoising algorithm for coal mine image based on coupled partial differential equations

针对煤矿复杂环境下矿井图像具有噪声大、照度低的问题,提出了一种基于二阶与四阶偏微分方程耦合的煤矿图像去噪算法。该算法利用差分曲率边缘检测算子将二阶与四阶偏微分方程模型有效耦合,保持图像边缘,利用尺度因子保护图像纹理细节。实验结果表明,该算法能很好地保持图像边缘、保护图像纹理细节,且收敛速度快,可避免阶梯效应。

In view of problems of high noise and low illumination of coal mine image under complicated circumstance in coal mine, the paper proposed a denoising algorithm for coal mine image based on coupled second-order and fourth-order partial differential equations. The algorithm uses difference curvature edge detection operator to couple the second-order and the fourth-order partial differential equation models effectively, so as to preserve image edge, and uses scale factor to preserve texture detail of the image. The experimental results show that the algorithm can preserve edge and texture detail of the image well, has fast convergence speed, and avoids staircase effect.