Open AccessImage Denoising Based on Adaptive Sector Rotation Median Filter
Author(s) -
Yuan-Bin Wang,
Huiting Huang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1769/1/012056
Subject(s) - median filter , salt and pepper noise , noise reduction , artificial intelligence , computer science , mathematics , image denoising , noise (video) , rotation (mathematics) , computer vision , algorithm , image (mathematics) , pattern recognition (psychology) , image processing
By analyzing the characteristics of different median filtering algorithms, an adaptive fan rotation median filtering method based on the standard median filtering method is proposed to restore the details of the image to the maximum extent for achieving better pepper and salt noise removal effect. The proposed method can change the window size adaptively according to the pollution degree in the window, and calculate the gray difference value for different areas, judge the correlation between the center point and different areas according to the gray difference value, and take the median value of the highest correlation area as output, which can restore the details of the image while removing the noise. The experimental results show that the new algorithm has a high similarity with the original image structure and a high peak signal-to-noise ratio after filtering, and can better recover the image details. Compared with other methods, the noise removal effect and detail recovery effect are better.