Abstract
Denoising is an important preprocessing step that aids many computer-aided diagnosis systems, computer graphics, and computer vision applications; however, the tradeoff between reducing noise and preserving details in images is not trivial, especially in medical images. Therefore, this paperwork proposes two weighted factors besides using two popular factors to investigate deeply the performance of the deep convolutional neural network and median filter in reducing different kinds of noise and mixed noise with various noise percentages. After the intensive analysis, the assessment results show that the convolutional Neural network outperformed the median in terms of denoising and detail preserving in reducing several noises, especially with images that are highly corrupted by specular noise. The efficiency rank in preserving details during reducing low and high ratios of different types of noises by each method was also rated. The proposed solutions can be used for automatic denoising of the mentioned noises with controlling the detail preserving using our proposed weighted factors.
Similar content being viewed by others
Data availability
Data will be available on a reasonable request.
References
Akagi M, Nakamura Y, Higaki T, Narita K, Honda Y, Zhou J, Yu Z, Akino N (2019) Awai K. Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT 29:6163–6171. https://doi.org/10.1007/s00330-019-06170-3
Azawi N (2021) Adaptive motion compensated spatial temporal filter of colonoscopy video. Iraqi J Sci 62(11):4148–4157. https://doi.org/10.24996/ijs.2021.62.11.33
Azawi N., Gaugh J. (2019) Motion Compensated Restoration of Colonoscopy Images. Conference: 9th international conference on computer science, engineering and applications, pp 243–256. https://doi.org/10.5121/csit.2019.90920
Baid A, Kotwal A, Bhalodia R, Merchant SN, Awate SP (2017) Joint desmoking, specularity removal, and denoising of laparoscopy images via graphical models and Bayesian inference. In: 2017 IEEE 14th international symposium on Biomedical imaging (ISBI 2017), pp 732–736
Cao J, Cai Z, Liang W (2020) A novel thresholding method for simultaneous seismic data reconstruction and denoising. J Appl Geophy 177:104027
Chen B, Yin J, Li Y (2017) Image noise removing using semi-supervised learning on big image data. In: 2017 IEEE third international conference on multimedia big data (BigMM), pp 338–345
Chen G, Wang H, Jian T, Xu C, Sun S (2020) Method for denoising and reconstructing radar HRRP using modified sparse auto-encoder. Chin J Aeronaut
Chen L, Chen X, Cui H, Long Y, Wu J (2021) Image enhancement in lensless inline holographic microscope by inter-modality learning with denoising convolutional neural network. Opt Commun 484:126682
Gonzalez RC, Wood RE (2018) Digital Image Processing, Fourth Edition
Goyal B, Dogra A, Agrawal S, Sohi BS, Sharma AM (2020) Image denoising review: from classical to state-of-the-art approaches. Inf Fusion 55:220–244
Huang L, Jiang H, Li S, Bai Z, Zhang J (2020) Two stage residual CNN for texture denoising and structure enhancement on low dose CT image. Comput Methods Prog Biomed 184:105115
Jin Y, Yu L, Li G, Fei S (2021) A 6-DOFs event-based camera relocalization system by CNN-LSTM and image denoising. Expert Syst Appl 170:114535
Kokil P, Sudharson S (2020) Despeckling of clinical ultrasound images using deep residual learning. Comput Methods Prog Biomed 194:105477
Lee S, Negishi M, Urakubo H, Kasai H, Ishii S (2020) Mu-net: multi-scale U-net for two-photon microscopy image denoising and restoration. Neural Netw 125:92–103
Lin P, Chen B, Cheng F, Huang S (2016) A morphological mean filter for impulse noise removal. J Disp Technol 12:344–350
Liu L, Chen L, Chen C, Tang Y, Pun C (2017) Weighted joint sparse representation for removing mixed noise in image. IEEE Trans Cybern 47:600–611
Liu Z, Yan W, Yang M (2018) Image denoising based on a CNN model. In: 2018 4th international conference on control, automation and robotics (ICCAR), pp 389–393
Liu L, Chen C, You X, Tang Y, Zhang Y, Li S (2018) Mixed noise removal via robust constrained sparse representation. IEEE Trans Circuits Syst Video Technol 28:2177–2189
Liu C, Abergel R, Gousseau Y, Tupin F (2020) Training CNNs on speckled optical dataset for edge detection in SAR. ISPRS J Photogramm Remote Sens
Malik J, Kiranyaz S, Gabbouj M (2021) Self-organized operational neural networks for severe image restoration problems. Neural Networks 135:201–211
Panetta K, Bao L, Agaian S (2018) A new unified impulse noise removal algorithm using a new reference sequence-to-sequence similarity detector. IEEE Access 6:37225–37236
Somasundaran BV, Soundararajan R, Biswas S (2018) Image denoising for image retrieval by cascading a deep quality assessment network. In: 2018 25th IEEE international conference on image processing (ICIP), pp 525–529
Srujana P, Kumar DS, Ramadevi B, Kiranmai B (2021) Comparison of image denoising using convolutional neural network (CNN) with traditional method. In: 2021 5th international conference on computing methodologies and communication (ICCMC), pp 826–831
Tian C, Xu Y, Zuo W (2020) Image denoising using deep CNN with batch renormalization. Neural Networks 121:461–473
Tian C, Xu Y, Li Z, Zuo W, Fei L, Liu H (2020) Attention-guided CNN for image denoising. Neural Networks 124:117–129
Tian C, Fei L, Zheng W, Xu Y, Zuo W, Lin C (2020) Deep learning on image denoising: an overview. Neural Networks 131:251–275
Wang Y, Dai Y, Liu X, Liu B, Guo X (2018) Study on the method of color image noise reduction based on optimal channel processing. IET Image Process 12:1545–1549
Xu G, Lin Y (2016) An efficient restoration algorithm for images corrupted with salt and pepper noise. In: 2016 9th international congress on image and signal processing, BioMedical engineering and informatics (CISP-BMEI), pp 184–188
Zhang P, Li F (2014) A new adaptive weighted mean filter for removing salt-and-pepper noise. IEEE Signal Process Lett 21:1280–1283
Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process 26:3142–3155
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There is no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Azawi, N. Performance comparison of deep convolution neural network and median filter in terms of denoising and detail preserving. Multimed Tools Appl 82, 45733–45745 (2023). https://doi.org/10.1007/s11042-023-16336-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-16336-3