High Density Noise Removal by Using Cascading Algorithms

Abstract

An advanced non-linear cascading filter algorithm for the removal of high density salt and pepper noise from the digital images is proposed. The proposed method consists of two stages. The first stage Decision base Median Filter (DMF) acts as the preliminary noise removal algorithm. The second stage is either Modified Decision Base Partial Trimmed Global Mean Filter (MDBPTGMF) or Modified Decision Based Unsymmetric Trimmed Median Filter (MDBUTMF) which is used to remove the remaining noise and enhance the image quality. The DMF algorithm performs well at low noise density but it fails to remove the noise at medium and high level. The MDBPTGMF and MDUTMF have excellent performance at low, medium and high noise density but these reduce the image quality and blur the image at high noise level. So the basic idea behind this paper is to combine the advantages of the filters used in both the stages to remove the Salt and Pepper noise and enhance the image quality at all the noise density level. The proposed method is tested against different gray scale images and it gives better Mean Absolute Error (MAE)

Proposed De-noising Algorithm

“…However, when used for modified images, both noise pixels and noise pixels are restored. The advantage of using a median filter is that it works well on blurred, thinning, or corner distortions in images in low noise densities while producing unpreserved edge details in higher noise densities close to the original image [16][17][18][19].…”

Öklid Mesafe Tabanlı Uyarlamalı Filtre Kullanılarak Tuz Biber Gürültüsü Giderimi

“…Karar Tabanlı Ortanca Filtresi (Decision Based Median Filter, DMF) kullanılan çalışmalarda, MF'den farklı olarak sadece tuz ve biber gürültüsünün olduğu piksellerde işlem yapılmaktadır [4,5]. Modifiye Karar Tabanlı Eşlenik Olmayan İşlenmiş Ortanca Filtresi (Modified Decision Based Unsymmetric Trimmed Median Filter, MDBUTMF) yöntemi kullanan çalışmalarda ise gürültülü piksel tespit edilmekte ve uygulanan pencere içerisindeki gürültülü piksellerin çıkarılmasıyla kalan piksellerin ortanca değeri hesaplanılmaktadır [5,8]. Bu filtre özellikle yüksek gürültü yoğunluğuna sahip görüntülerde iyi çalıştığı görülmektedir.…”

“…Bu sonuçlardan görüldüğü gibi önerilen yaklaşım düşük gürültü yoğunluğunda görsel olarak iyi sonuçlar verdiği gibi gürültü yoğunluğu çok fazla olduğu durumda da görsel olarak gayet iyi sonuçlar vermektedir. [4], [5] (d) MDBUTMF [5]- [8] (e) BPDF [15] (f) DAMF [16]  PSNR değerleri incelendiğinde önerlilen filtre ile literatürdeki diğer filtrelere göre yaklaşık olarak 0.5 dB ile 2 dB arasında bir kazanç sağlandığı anlaşılmaktadır.…”

Fast adaptive and selective mean filter for the removal of high‐density salt and pepper noise

“…Various median filters exist in the literature to remove salt and pepper noise at higher densities [7][8][9][10][11][12][13][14][15][16][17][18][19]. Several other filters that use different methodologies have also been proposed [20][21][22][23][24][25] for removing high-density salt and pepper noise.…”

“…In this paper, the performance of the various median filters used in removing salt and pepper noise is analysed. Most of the median filters [7][8][9][10][11][12][13][14][15][16][17][18][19] in the literature work in two stages. The first stage detects the noisy pixels, while the second stage restores the identified noisy pixels.…”