Image denoising based on improved bidimensional empirical mode decomposition thresholding technology
In this paper, a novel image denoising methodology based on improved bidimensional empirical mode decomposition and soft interval thresholding technique is proposed. First, a noise compressed image is constructed. Then, the noise compressed image is decomposed by means of bidimensional empirical mode decomposition (BEMD) into a series of intrinsic mode functions (IMFs), which are separated into signal-dominant IMFs and noise-dominant IMFs using a similarity measure based on ℓ2-norm and a probability density function, and a soft interval thresholding technique is used adaptively to remove the noise inherent in noise-dominant IMFs. Finally, a denoised image is reconstructed by combining the signal-dominant IMFs and the denoised noise-dominant IMFs. The performance of the proposed denoising method is evaluated by using multiple images with different types of noise, and results from the proposed method are compared with those of other conventional methods in various noisy environments. Simulation results demonstrate that the proposed denoising method outperforms other denoising methods in terms of peak signal-to-noise ratio, mean square error and energy of the first IMF.
KeywordsBEMD Image denoising Noise compression
This work is supported by the National Natural Science Foundation of China (Grant No. 51375087, 51405203) and the Transformation Program of Science and Technology Achievements of Jiangsu Province (Grant No. BA2016139).
Compliance with ethical standards
Conflicts of interest
The authors declare no conflict of interest.
- 1.Abergel R, Louchet C, Moisan L, Zeng T (2015) Total variation restoration of images corrupted by poisson noise with iterated conditional expectations. In: International Conference on Scale Space and Variational Methods in Computer Vision. Springer, pp 178–190Google Scholar
- 12.Deering R, Kaiser JF (2005) The use of a masking signal to improve empirical mode decomposition. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'05). IEEE, pp: 485–488Google Scholar
- 13.Deledalle CA, Tupin F, Denis L (2010) Poisson NL means: Unsupervised non local means for Poisson noise. IEEE Int Conf Image Process. IEEE: 801–804. https://doi.org/10.1109/ICIP.2010.5653394
- 16.Flandrin P, Gonçalves P, Rilling G (2005) EMD equivalent filter banks, from interpretation to applications. In: Dua J (ed) Hilbert–Huang transform and its applications, 2rd end. World Scientific, Singapore, pp 99–116Google Scholar
- 17.Gan L, Zhou L, You X (2014) A new GPR image de-nosing method based on BEMD. 2014 I.E. Int Conf Secur, Pattern Ana, Cybern (ICSPAC): 328–331Google Scholar
- 19.Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Yen N, Tung CC (1971) Liu HH (1998) the empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc Roy Soc Lond A 454:903–995. https://doi.org/10.1098/rspa.1998.0193 CrossRefzbMATHGoogle Scholar
- 26.Labate D, Foresta FL, Occhiuto G, Morabito FC, Lay-Ekuakille A, Vergallo P (2013) Empirical mode decomposition vs. wavelet decomposition for the extraction of respiratory signal from Single-Channel ECG: a comparison. IEEE Sensors J 13(7):2666–2674. https://doi.org/10.1109/JSEN.2013.2257742 CrossRefGoogle Scholar
- 27.Louchet C, Moisan L (2008) Total variation denoising using posterior expectation. 2008 Proc 16nd Eur Sign Process Conf (EUSIPCO). IEEE: 1–5Google Scholar
- 28.Louchet C, Moisan L (2014) Total variation denoising using iterated conditional expectation. 2014 Proc 22nd Eur Sign Process Conf (EUSIPCO). IEEE: 1592–1596Google Scholar
- 37.Wang SH, Muhammad K, Lv YD, Sui YX, Han LX, Zhang YD (2018) Identification of alcoholism based on wavelet Renyi entropy and three-segment encoded Jaya algorithm. Complexity. https://doi.org/10.1155/2018/3198184