This paper presents a novel method for the detection of binary- and random-valued impulsive noise in contaminated images. The noise detector has been developed to classify the certain intensity image pixels as corrupted or uncorrupted based on their relative position. To perform such classification, we regard noise as random points and propose to use the properties of random point patterns that are formed based on a noisy image. Pixels of each image intensity are checked by what type of point pattern they form based on the Clark–Evans test. In the case of random or regular type, pixels of this intensity are classified as noise. For intensity pixels designated as a cluster, the search of isolated points is performed. In case of a homogeneity test fail, they are also classified as noise. The proposed technique can be applied to color images. Extensive simulation experiments indicate that the proposed detection approach outperforms many well-known means.

本文提出了一种检测受污染图像中二进制和随机值脉冲噪声的新方法。已经开发了噪声检测器以根据它们的相对位置将特定强度的图像像素分类为损坏的或未损坏的。为了执行这种分类，我们将噪声视为随机点，并建议使用基于噪声图像形成的随机点模式的特性。根据克拉克-埃文斯检验，每个图像强度的像素通过它们形成的点图案类型进行检查。在随机或规则类型的情况下，这种强度的像素被归类为噪声。对于指定为簇的强度像素，执行孤立点的搜索。如果同质性测试失败，它们也被归类为噪声。所提出的技术可以应用于彩色图像。