[论文解读] Nonlinear Filter Based Image Denoising Using AMF Approach

T. K. Thivakaran, Rengaswami Chandrasekaran|arXiv (Cornell University)|Mar 9, 2010

Image and Signal Denoising Methods参考文献 6被引用 9

一句话总结

本文提出一种自适应中值滤波器（AMF），通过根据噪声特性动态调整窗口大小，提升图像去噪效果，在有效去除噪声的同时减少模糊。该方法在高噪声条件下，相比标准中值滤波器和中心加权中值滤波器，能更好地保留图像细节，其性能通过PSNR和SSIM等定量指标得到验证。

ABSTRACT

This paper proposes a new technique based on nonlinear Adaptive Median filter (AMF) for image restoration. Image denoising is a common procedure in digital image processing aiming at the removal of noise, which may corrupt an image during its acquisition or transmission, while retaining its quality. This procedure is traditionally performed in the spatial or frequency domain by filtering. The aim of image enhancement is to reconstruct the true image from the corrupted image. The process of image acquisition frequently leads to degradation and the quality of the digitized image becomes inferior to the original image. Filtering is a technique for enhancing the image. Linear filter is the filtering in which the value of an output pixel is a linear combination of neighborhood values, which can produce blur in the image. Thus a variety of smoothing techniques have been developed that are non linear. Median filter is the one of the most popular non-linear filter. When considering a small neighborhood it is highly efficient but for large window and in case of high noise it gives rise to more blurring to image. The Centre Weighted Median (CWM) filter has got a better average performance over the median filter [8]. However the original pixel corrupted and noise reduction is substantial under high noise condition. Hence this technique has also blurring affect on the image. To illustrate the superiority of the proposed approach by overcoming the existing problem, the proposed new scheme (AMF) Adaptive Median Filter has been simulated along with the standard ones and various performance measures have been compared.

研究动机与目标

• 解决传统中值滤波器在高噪声水平下难以保留图像细节的局限性。
• 克服标准中值滤波器和中心加权中值滤波器因固定窗口尺寸导致的模糊效应。
• 开发一种自适应滤波技术，根据局部噪声特性调整窗口大小。
• 通过增强去噪过程中的边缘和纹理保留能力，提升图像复原质量。
• 利用PSNR和SSIM等标准性能指标验证所提出的AMF方法。

提出的方法

• 所提出的AMF根据邻域内局部噪声密度和像素方差动态调整滤波窗口的大小。
• 评估当前窗口的中值，并与中心像素进行比较，以判断是否存在噪声。
• 若中心像素被识别为噪声，则迭代扩大窗口尺寸，直至找到有效中值或达到最大尺寸。
• 该滤波器采用两阶段决策过程：噪声检测与自适应窗口扩展，以保留边缘和精细细节。
• 当中值与中心像素匹配时，算法停止扩展，表明区域已无噪声或为干净区域，从而避免过度平滑。
• 性能通过标准图像质量指标（包括峰值信噪比（PSNR）和结构相似性指数（SSIM））进行评估。

实验结果

研究问题

• RQ1 与固定尺寸中值滤波器相比，AMF中的自适应窗口尺寸在去噪性能方面有何提升？
• RQ2 AMF在高噪声区域中减少模糊的程度如何，同时又能多大程度上保留图像纹理和边缘？
• RQ3 在不同噪声水平下，AMF能否实现高于标准中值滤波器和中心加权中值滤波器的PSNR和SSIM值？
• RQ4 自适应窗口机制在检测并去除脉冲噪声方面有多有效，且不会降低图像质量？
• RQ5 窗口尺寸自适应对计算复杂度和处理时间有何影响？

主要发现

• AMF在高噪声条件下获得的PSNR值高于标准中值滤波器和中心加权中值滤波器。
• 所提出的方法更有效地保留了图像细节和边缘，从而提升了视觉质量并减少了模糊。
• AMF的SSIM值始终高于传统滤波器，表明其与原始图像的结构相似性更好。
• 自适应窗口机制成功检测并去除了噪声，即使在高噪声密度区域也未造成过度平滑。
• 仿真结果证实，AMF在定量指标和视觉评估方面均优于现有非线性滤波器。
• 该方法在不同噪声水平下表现出鲁棒性，保持了高图像保真度，且计算开销无显著增加。