A systematic review of state-of-the-art noise removal techniques in digital images

Bindal, Nishant; Ghumaan, Rajanbir Singh; Sohi, Prateek Jeet Singh; Sharma, Nikhil; Joshi, Hem Dutt; Garg, Bharat

doi:10.1007/s11042-022-12847-7

Cited by 4 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, because the validation of noisy image training involves another set of random noise, the network cannot converge to the validation target for every validation set. As a result, the network exhibits behavior analogous to averaging all gradients, causing the randomly distributed noise to appear as an average by (2). Considering noise as a zero-mean Gaussian distribution, allowing the network's output to reveal clean image features hidden within the noisy mask.…”

Section: Image Denoising With Noise2noise Learning Approachmentioning

confidence: 99%

See 1 more Smart Citation

Self-Augmented Noisy Image for Noise2Noise Image Denoising

Limsuebchuea,

Duangsoithong,

Phukpattaranont

2024

IEEE Access

View full text Add to dashboard Cite

Image denoising is a critical task in image processing aimed at removing noise artifacts. Typically, supervised deep learning often necessitates a large number of pairs of noisy and noise-free images for training. Noise2Noise techniques have demonstrated efficiency in noise removal without relying on a noise-free ground truth. This is achieved through a learning process that approaches input to target points, balancing results across all training inputs. While Noise2Noise can be adapted for single image denoising, it still faces challenges in single image and blind noise scenarios. To address this issue, our research introduces the concept of self-augmented noisy images for self-supervised Noise2Noise single image denoising. The proposed method leverages the behavior of the training process, which strives to balance the loss values appropriately for each training set. By utilizing the same noisy image for both input and validation to learn self-identification, it produces another set of noisy images that mimic the input noisy images. From the experimental results, measured using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics, it is evident that the proposed self-augmented strategy enables Noise2Noise to remove noise in single image scenarios. Additionally, it achieves performance comparable to other unsupervised denoising methods without requiring additional augmentation manipulations.INDEX TERMS image denoising, single image denoising, blind noise, self-supervised, self-augmentation.

show abstract

Section: Image Denoising With Noise2noise Learning Approachmentioning

confidence: 99%

“…Image denoising is a crucial task in image processing. Noisy images [1], [2], arise from disruptive signals added to the image data. These signals can originate from sources such as cameras with inherent noise or tools that introduce interference signals into the image.…”

mentioning

confidence: 99%

Self-Augmented Noisy Image for Noise2Noise Image Denoising

Limsuebchuea,

Duangsoithong,

Phukpattaranont

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

FIDOC: A New Combination of Fuzzy Impulse Noise Detection and Open-Close Filtering

Sussner,

González-Hidalgo

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Adaptively Directed Image Restoration Using Resilient Backpropagation Neural Network

Nawaz

Ṣiddiqi

Almadhor

2023

Int J Comput Intell Syst

View full text Add to dashboard Cite

In this modern era, visual data transmission, processing, and analysis play a vital role in daily life. Image denoising is the process of approximately estimating the original version of a degraded image. The presence of unexpected noise (e.g., fixed, random, and Gaussian) is the root cause of degradation, which has been reduced to some extent by many linear and non-linear filters based on a median value. The real issue is developing a strategy that should be generalized enough to effectively restore an image corrupted with multi-nature noise. Many researchers have developed novel concepts, but their tactics must acquire the highest performance in this area. This article proposes a constrained strategy for this problem, i.e., an adaptively directed denoising filter (ADD filter) based on a neural network. It consists of three major stages: training, filtering, and enhancing. First, we train a feed-forward back-propagation neural network on noisy and noise-free pixels for effective differentiation. Second, we apply a one-pass selective filter to the noisy image. The objective of this one-pass filter is to minimize noise using an adaptive median or directional filter based on density. Finally, the iterative directional filter is applied to the pre-processed image to enhance its visual quality. The extensive experiments depict that the proposed system has achieved better subjective results and improved local (structural similarity) and global (peak signal-to-noise ratio or mean square error) statistical measures.

show abstract

A systematic review of state-of-the-art noise removal techniques in digital images

Cited by 4 publications

References 32 publications

Self-Augmented Noisy Image for Noise2Noise Image Denoising

Self-Augmented Noisy Image for Noise2Noise Image Denoising

FIDOC: A New Combination of Fuzzy Impulse Noise Detection and Open-Close Filtering

Adaptively Directed Image Restoration Using Resilient Backpropagation Neural Network

Contact Info

Product

Resources

About