Two new methods of adaptive median filtering of impulse noise in images are proposed in the paper. The first method is based on the joint application of iterative processing and transformation of the result of median filtering using the Lorentzian function. The second method uses alternative masks of median filter, calculated using the Euclidean metric. This approach has made it possible to reduce the size of the processed area without the loss in quality for low-intensity noise. The experimental part of the article shows the results of comparison of the performance of the proposed methods with the known methods. We used three different images distorted by impulse noise with pixel distortion probabilities ranging from 1 % up to 99 %. The numerical evaluation of the quality of image denoising based on the peak signal to noise ratio (PSNR) and the structural similarity (SSIM) has shown that the proposed method shows a better result of processing in all the cases considered, as compared with the known approaches. The results obtained in the paper may find wide practical applications when processing satellite and medical imagery, geophysical data, and in other areas of digital image processing.

Images taken with different sensors and transmitted through different channels can be noisy. In such conditions, the image most often suffers from random-valued impulse noise. Denoising an image is an important part of image preprocessing before recognition by a neural network. The accuracy of image recognition by a neural network directly depends on the intensity of image noise. This paper presents a three-stage image cleaning and recognition system, which includes a developed detector of pulsed noisy pixels, a filter for cleaning found noisy pixels based on an adaptive median, and a neural network program for recognizing cleaned images. It was noted that at low noise intensities, cleaning is practically not required, but noise with an intensity of more than 10% can seriously damage the image and reduce recognition accuracy. As a training base for noise, cleaning, and recognition, the CIFAR10 digital image database was used, consisting of 60,000 images belonging to 10 classes. The results show that the proposed neural network recognition system for images affected by to random-valued impulse noise effectively finds and corrects damaged pixels. This helped to increase the accuracy of image recognition compared to existing methods for cleaning random-valued impulse noise.

The paper proposes a generalized method of adaptive median impulse noise filtering for video data processing. The method is based on the combined use of iterative processing and transformation of the result of median filtering based on the Lorentz distribution. Four different combinations of algorithmic blocks of the method are proposed. The experimental part of the paper presents the results of comparing the quality of the proposed method with known analogues. Video distorted by impulse noise with pixel distortion probabilities from 1% to 99% inclusive was used for the simulation. Numerical assessment of the quality of cleaning video data from noise based on the mean square error (MSE) and structural similarity (SSIM) showed that the proposed method shows the best result of processing in all the considered cases, compared with the known approaches. The results obtained in the paper can be used in practical applications of digital video processing, for example, in systems of video surveillance, identification systems and control of industrial processes.