Abstract
Image noise is undesirable that can negatively affect the quality of digital images. It reduces the image quality and increases the processing failure ratio. It is highly recommended to remove the noise, and before removing the noise, we have to know the type of noise and estimate the parameters of noise for developing effective noise reduction techniques. This study introduces a method to effectively detect, recognize, and estimate image noise of various types (Gaussian, lognormal, Rayleigh, salt and pepper, and speckle). The proposed model consists of four stages: the first stage is detecting the noise in an image using a convolutional neural network. The second stage classifies the noisy images into one of five types of noise using a new method based on a combination of deep wavelets and support vector machines (SVM) classifier. The third stage involves estimating the parameters of the noise using maximum likelihood estimation (MLE). Finally, choosing the most suitable noise reduction technique for each type using linear and nonlinear filters and showing the capability of the suggested technique in estimating multiple noises commonly present in digital images. The proposed method utilizes a likelihood function derived from the MLE model for each noise type to estimate the noise parameters. Then used to select the most suitable noise reduction technique for each type. The quality of the denoised images is calculated utilizing the peak signal-to-noise ratio (PSNR) as the evaluation metric. The results show that the combination of wavelets with machine learning, specifically SVM, can highly enhance the results, where the accuracy was 93.043% through many experiments conducted to build a sturdy classification model. The MLE-based noise estimation method is also a reliable and accurate method for image noise estimation, especially for Gaussian, salt and pepper, lognormal, and Rayleigh noise. However, for highly noisy types such as speckle noise, further research is required to improve the estimation accuracy. This study contributes to the development of more effective noise estimation methods for improving the quality of digital images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Babaei-Mahani A, Sheikhzadeh H, Cheriet M (2014) A survey on image denoising using fuzzy logic. J Electron Imaging 23(1):1–26
Asano S, Kamata S, Miyatake T (2019) Survey of noise reduction methods for digital images. J Signal Process 23(1):1–10. https://doi.org/10.2299/jsp.23.1
Ismail M, Usman M, Daud A (2018) A comparative study of noise estimation methods for digital images. EURASIP J Image Video Process 2018(1):16. https://doi.org/10.1186/s13640-018-0246-9
Kirmizitas K, Besli N (2022) Image and texture independent deep learning noise estimation using multiple frames Elektron. ir Elektrotechnika 28:42–47
Patil S, Sherekar SS (2019) Noise detection and classification using machine learning: a review. J Ambient Intell Humaniz Comput 10(1):169–183. https://doi.org/10.1007/s12652-018-0896-2
Ponomaryov V, Egiazarian K (2012) Non-stationary noise estimation and filtering in the image and video processing. EURASIP J Adv Sign Process 2012(1):1–2
Egiazarian K, Foi A, Katkovnik V, Oksanen L (2017) Noise variance estimation in additive Gaussian noise: a review of methods and challenges. Digital Signal Process 70:1–19
Li C, Guo S, Porikli F (2013) No-reference quality assessment for natural videos via blind quality estimator in a spatiotemporal domain. IEEE Trans Circ Syst Video Technol 23(3):505–515. https://doi.org/10.1109/TCSVT.2012.2231520
Liu J, Wu W, Zuo W, Zhang D (2020) An efficient noise level estimation method for real images. IEEE Trans Image Process 29:559–570
Chuah JH, Khaw HY, Soon FC, Chow C (2017) Detection of gaussian noise and its level using deep convolutional neural network. In: Procceding of the 2017 IEEE region 10 conference (TENCON), Malaysia, November 5–8, pp 2447–2450
Ponomarenko M, Gapon N, Voronin V, Egiazarian K (2018) Blind estimation of white Gaussian noise variance in highly textured images. IS T Int Symp Electron Imag Sci Technol. https://doi.org/10.2352/ISSN.2470-1173.2018.13.IPAS-382
Fang Z, Yi X (2019) A novel natural image noise level estimation based on flat patches and local statistics. Multimed Tools Appl 78(13):17337–17358. https://doi.org/10.1007/s11042-018-7137-4
Jiang P, Wang Q, Wu J (2020) Efficient noise-level estimation based on principal image texture. IEEE Trans Circuits Syst Video Technol 30(7):1987–1999. https://doi.org/10.1109/TCSVT.2019.2912319
Liu F, Song Q, Jin G (2020) The classification and denoising of image noise based on deep neural networks. IEEE Access 7:2194–2207. https://doi.org/10.1007/s10489-019-01623-0
Hiremath PS (2021) Identification of noise in an image using artificial neural network. Int J Eng Res Technol 10(2):345–348
Chin SC, Chow CO, Kanesan J, Chuah JH (2022) A study on distortion estimation based on image gradients. Sensors 22(2). https://doi.org/10.3390/s22020639
Objois É, Okumuş K, Bähler N (2022) Target aware poisson-gaussian noise parameters estimation from noisy images, pp 1–10. http://arxiv.org/abs/2210.12142
Sarigul M, Ozyildirim BM, Avci M (2019) Differential convolutional neural network. Neural Netw 116:279–287. https://doi.org/10.1016/j.neunet.2019.04.013
Soro B, Lee C (2019) A wavelet scattering feature extraction approach for deep neural network based indoor fingerprinting localization. Sensors (Switzerland) 19(80). https://doi.org/10.3390/s19081790
Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Transact Intell Syst Technol 27(3):1–27. https://doi.org/10.1145/1961189.1961199
Bharadwaj Prakash KB, Kanagachidambaresan GR (2021) Pattern recognition and machine learning. EAI/Springer Innovations in Communication and Computing. https://doi.org/10.1007/978-3-030-57077-4_11
McLachlan GJ, Lee SX, Rathnayake SI (2019) Finite mixture models. Ann Rev Stat Appl 6:355–378
Myung IJ (2003) Tutorial on maximum likelihood estimation. J Math Psychol 47(1):90–100
Umbaugh SE (2018) Image processing and analysis. In: Digital image processing and analysis: applications with MATLAB and CVIPtools, 3rd ed., Boca Raton, FL, USA, CRC Press, pp 144–152
Zhang X (2016) Image denoising using local Wiener filter and its method noise. Optik 127(17):6821–6828
Sarjanoja S, Boutellier J, Hannuksela H (2015) BM3D image denoising using heterogeneous computing platforms. In: 2015 conference on design and architectures for signal and image processing (DASIP), Krakow, pp 1–8. https://doi.org/10.1109/DASIP.2015.7367217
Sun Z, Meikle S, Calamante F, Cowin GJ (2022) CONN-NLM: a novel means filter for PET-MRI denoising. IEEE Access 16:1–14. https://doi.org/10.1109/ACCESS.2022.3162002
Jaiswal A, Upadhyay J, Somkuwar A (2014) "Image denoising and quality measurements by using filtering and wavelet-based techniques. AEU-Int J Electron Commun 68(8):699–705
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Al Mudhafar, R.A., Abbadi, N.K.E. (2024). Comprehensive Approach for Image Noise Analysis: Detection, Classification, Estimation, and Denoising. In: Sharma, D.K., Peng, SL., Sharma, R., Jeon, G. (eds) Micro-Electronics and Telecommunication Engineering. ICMETE 2023. Lecture Notes in Networks and Systems, vol 894. Springer, Singapore. https://doi.org/10.1007/978-981-99-9562-2_50
Download citation
DOI: https://doi.org/10.1007/978-981-99-9562-2_50
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-9561-5
Online ISBN: 978-981-99-9562-2
eBook Packages: EngineeringEngineering (R0)