СРАВНИТЕЛЬНЫЙ АНАЛИЗ ДВУХ СПОСОБОВ ФИЛЬТРАЦИИ ДЛЯ УСТРАНЕНИЯ ШУМА В ИЗОБРАЖЕНИИ РАЗНОЙ СТЕПЕНИ ЗАШУМЛЕННОСТИ

Abstract

In modern photography and video technology, any image in the process of its creation isdistorted by various types of noise. There are various types of noise, but in practice, impulsive andGaussian noise models are the most common. Attenuation of the effect of noise is achieved by filtering.At the moment, there is no universal filter that suppresses noise data at various intens itiesof distortion. Therefore, an important aspect is to determine the field of application of eachtype of filter when suppressing noise in the image and creating a filter, consisting of a combinationof different filtering methods for optimal image cleaning. The article presents a comparativeanalysis of median filtering and Wiener filtering to eliminate impulse and Gaussian noise inthe image with different degrees of noise. For modeling, we used one image, separately distortedby impulse and separately by Gaussian noise with pixel distortion probabilities from 1% to99% inclusive. Filtration was performed with windows equal to 3x3 and 5x5. As a result, weobtained numerical estimates of the image filtering quality based on the peak signal-to-noiseratio (PSNR). On the basis of the data obtained, the application of the investigated filters, theirmodifications, advantages and disadvantages were analyzed, as well as recommendations fortheir use were given. As a result of a comparative analysis of the studied types of filtering fornoisy images, it was found that the median filter with a 3x3 window copes better with imagecleaning from low-intensity impulse noise and with a 5x5 window - with image cleaning with anaverage noise intensity. Also, the median filter does a better job of filtering out Waussian noiseat its medium and high rms deviations. The Wiener filter with 3x3 and 5x5 windows better fi ltersGaussian noise at small values of its root-mean-square deviation. Also, the Wiener filtercopes better with impulse noise with relatively high noise power.