Perbandingan Algoritma untuk Mereduksi Noise pada Citra Digital

Ginanjar Setyo Nugroho; Gulam Hazmin

doi:10.51519/journalita.volume3.isssue2.year2022.page159-174

Authors

Ginanjar Setyo Nugroho Universitas PGRI Yogyakarta
Gulam Hazmin Universitas PGRI Yogyakarta

DOI:

10.51519/journalita.volume3.isssue2.year2022.page159-174

Keywords:

Digital Image Processing, Image Restoration, Noise Reduction, Filtering Algorithm

Abstract

Image restoration is one of the stages in the field of Digital Image Processing. Image restoration is objective, in the sense that restoration techniques tend to be based on mathematical or probabillistic models of image degradation. The mathematical algorithm to reduce noise in digital images in this study uses 8 filtering algorithm methods. The purpose of this study is to compare 8 filtering algorithm and conclude which algorithm is the best for reducing noise in digital images. The method for generating noise uses Rayleigh Noise and Erlang (Gamma) Noise. The algorithm for reducing noise is Arithmetic Mean Filter, Geometric Mean Filter, Harmonic Mean Filter, Contraharmonic Mean Filter, Geometric Mean Filter, Harmonic Mean Filter, Contraharmonic Mean Filter, Median Filter, Maximum Filter, Minimum Filter, and Midpoint Filter. The measurement to determine which algorithm is the best using Root Mean Square Error (RMSE). Tests were carried out on 15 digital images by testing 1200 times. The conclusion of this study is that the best algorithm for noise reduction is Median Filter by resulting the smallest RMSE value of 6.0860942.

References

R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed. Pearson Education Limited, 2018.

G. Gupta, “Algorithm for Image Processing Using Improved Median Filter and Comparison of Mean, Median and Improved Median Filter,” Int. J. Soft Comput., no. 5, pp. 304–311, 2011.

S. Zhang, C. Pei, D. Sun, W. Liu, and L. Cao, “Industrial Image Enhancement Method Based on Cloud Edge Fusion,” Wirel. Commun. Mob. Comput., vol. 2022, 2022.

Y. Jiang and C. Chen, “Partial Differential Equation Noise Reduction Model and Fuzzy Image Processing in Optimal Application of Sports Dance Exercise Training Mode,” Wirel. Commun. Mob. Comput., vol. 2022, pp. 1–9, 2022.

A. Wedianto, H. L. Sari, and Y. S. H, “Analisa Perbandingan Metode Filter Gaussian, Mean dan Median terhadap Reduksi Noise,” J. Media Infotama, vol. 12, no. 1, pp. 21–30, 2016.

A. Y. Nasution and G. Ginting, “Implementasi Metode Harmonic Mean Filter Dan Canny untuk Mereduksi Noise pada Citra Digital,” J. Pelita Inform., vol. 6, no. 1, pp. 72–76, 2017.

M. Fitri, “Implementasi Reduksi Noise Pada Citra Ultrasonografi (USG) Menggunakan Metode Mean Filter,” J. Pelita Inform., vol. 7, no. 3, pp. 433–435, 2019.

D. Agusti and A. A. Nababan, “Penerapan Metode Harmonic Mean Filter Dalam Mereduksi Gaussian Noise Pada Citra Digital,” J. Nas. Komputasi dan Teknol. Inf., vol. 5, no. 3, pp. 565–571, 2022.

R. R. Fiska and A. Allwine, “Perancangan Aplikasi Perbaikan dengan Reduksi Noise pada Citra dengan Metode Geometric Mean Filter,” J. Bisantara Inform., vol. 3, no. 2, pp. 1–12, 2019.

M. Furqan, S. Sriani, and Y. K. Siregar, “Perbandingan Algoritma Contraharmonic Mean Filter dan Arithmetic Mean Filter untuk Mereduksi Exponential Noise,” JISKA (Jurnal Inform. Sunan Kalijaga), vol. 5, no. 2, pp. 107–115, 2020.

P. B. N. Simangunsong, “Reduksi Noise Pada Citra Digital Menggunakan Metode Arithmetic Mean Filter,” MEANS (Media Inf. Anal. dan Sist., vol. 02, no. 02, pp. 16–18, 2017.

P. B. N. Simangunsong, “Reduksi Noise Salt And Pepper Pada Citra Digital Menggunakan Metode Contraharmonic Mean Filter,” MEANS (Media Inf. Anal. dan Sist., vol. 2, no. 1, pp. 16–18, 2017.

Massachusetts Institute of Technology, “Rayleigh Noise Generator.” [Online]. Available: https://lost-contact.mit.edu/afs/inf.ed.ac.uk/group/teaching/matlab-help/R2016b/comm/ref/rayleighnoisegenerator.html. [Accessed: 24-Jul-2022].