基于自由纹理的决策滤波算法

Free texture based decision filter algorithm

为了克服当前的滤波算法在脉冲噪声滤除上的缺陷,进一步提高算法的去噪性能,在当前滤波算法的基础上,提出了基于自由纹理的决策滤波算法,首次提出自由纹理的概念。算法先根据灰度最值进行噪声检测,然后根据噪声与非噪声像素在分布上的不同特征,进一步运用自由纹理将噪声与灰度取最值的非噪声像素区分开。基于自由纹理将7×7邻域中的非噪声像素进行纹理分组,取最大自由纹理分组中非噪声像素的中值进行去噪。仿真实验的结果证明,基于自由纹理的决策滤波算法能够更加准确地检测噪声,并且客观的峰值信噪比和图像增强因子以及主观的视觉效果两方面的度量标准证明,算法的去噪性能显著优于当前的滤波算法。

For solving the problems of existing filters in removing impulse noise and improving the denoising performance,a free texture based decision filter algorithm is proposed based on the current filters,a free texture concept is proposed for the first time.The minimum and maximum intensity values of the dynamic range on the noisy image are used to detect the noisy pixels.Based on the different characteristics of the noisy pixel and the noise free pixel in the distribution,a free texture is used to further discriminate the noisy pixels from the noise free pixels whose intensities are minimum and maximum values.The noise free pixels in 7×7 neighborhood are divided into texture groups based on the free texture.The median of noise free pixels in the maximal free texture group is used to replace the noisy pixel.Simulation results prove that the algorithm can detect noise more accurately and its denoising performance outperforms the existing distinguished filters on peak signal-to-noise ratio(PSNR),image enhancement factor and visual representation at all noise densities.