Deep CNN for removal of salt and pepper noise

Xing, Yan; Xu, Jian; Tan, Jieqing; Li, Daolun; Zha, Wenshu

doi:10.1049/iet-ipr.2018.6004

Cited by 27 publications

(16 citation statements)

References 27 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Out of several types of image noise that occurs during image acquisition and transmission, the impulse noise is one of common types of noise which includes salt-and-pepper noise (SPN) [19]- [21] and random-valued impulse noise [22], [23]. SPN is caused by sudden disturbances in the signal and the pixels affected by SPN hold a maximum or a minimum gray value.…”

Section: Resultsmentioning

confidence: 99%

Noise Reduction on Bracketed Images for High Dynamic Range Imaging

Shim¹

2020

IJACSA

View full text Add to dashboard Cite

The quality of a high dynamic range (HDR) image produced from bracketed images taken at different camera exposure times can be degraded by noise contained in bracketed images. In this paper, we propose a noise reduction method on bracketed images based on exposure time ratio. First, for each pixel pair of a same scene point lying on two different images, the ratio of their intensity values is compared with the ratio of exposure times of the images on which the pixels are lying. If the compared ratios are close, these two pixels are included in noisefree pixels set. The complement of noise-free pixels set is defined as noisy pixels set. Then, the intensity value of each pixel in noisy pixels set is corrected by its expected value computed from noisefree pixel of the same scene point lying on another image. Experimental results show that all the noisy intensity values can be correctly restored from noise-free pixels except the saturated pixels. Denoising results by PSNR show that the proposed method outperforms the other recent denoising methods such as based-on pixel density filter (BPDF), noise adaptive fuzzy switching median filter (NAFSMF), and adaptive Riesz mean filter (ARmF).

show abstract

Section: Resultsmentioning

confidence: 99%

Noise Reduction on Bracketed Images for High Dynamic Range Imaging

Shim¹

2020

IJACSA

View full text Add to dashboard Cite

show abstract

“…1) Qualitative Evaluation: First, we qualitatively compared the proposed method (OAGS+CRNs) with different benchmark SP denoising methods, including MDBUTMF [11], NAFSMF [8], DAMF [12], FASMF [13], and Xing's [28]. Note that we re-train Xing's [28] with our training dataset for a fair comparison.…”

Section: B Comparisons Of Benchmark Methodsmentioning

confidence: 99%

“…However, it does not work for impulse noise and high-density image noise, where few noise-free pixels are available, causing it to fail to remove noise. Xing et al [28] proposed to remove SP noise using multiple denoisers based on convolutional neural networks (CNN), each of which is for a different noise scale. However, an obvious limitation is that it is less applicable to require multiple denoisers for various noise ratios.…”

Section: B Image Denoising Based On Deep Neural Networkmentioning

confidence: 99%

Image Impulse Noise Removal Using Cascaded Filtering Based on Overlapped Adaptive Gaussian Smoothing and Convolutional Refinement Networks

Peng

Huang

2021

IEEE Open J. Comput. Soc.

View full text Add to dashboard Cite

Impulse noise is often introduced to images when captured through image sensors due to sharp and sudden disturbances in the image signal, analog-to-digital converter errors, sensor temperature, etc., severely degrading their visual quality. Therefore, it is essential to develop an effective method to remove image noise. We propose a novel image denoising method for "salt-and-pepper" (SP) noise, using cascaded filtering based on overlapped adaptive Gaussian smoothing (OAGS) and the convolutional refinement networks (CRNs). First, the noisy input image can be preliminarily denoised by OAGS, where the noisy pixels are removed and recovered. The CRNs refine the result by restoring fine details for the denoised image. Through extensive experimental results, we demonstrate the proposed method substantially outperforms other state-of-the-art denoising methods, especially for high-density SP noise.

show abstract

“…Wang et al [34] proposed a variational method to automatically classify noise according to different statistical parameters and integrated the CNN regularizer to improve quality of the restored images significantly. Xing et al [35] employed CNN with the multi-layer structure to remove salt and pepper noise. In [36], a deep CNN (DCNN) is used to remove Gaussian noises, where residual learning is employed to separate noise from noisy observation.…”

Section: Related Workmentioning

confidence: 99%

Noise Removal in Embedded Image With Bit Approximation

Zhang

Tang

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Stego-images are often contaminated by interchannel noise or active noise attack when communicating on the Web. And it is challenging to restore embedded image from corrupted stego-image. This paper studies a kNN-bit approximation algorithm to remove noises in embedded image. The proposed algorithm distinguishes reliable bits from extracted bits, and estimates pixel values by keeping reliable bits unchanged and correcting unreliable bits. Specifically, the 8 th (highest) unreliable bit of a pixel can be approximated with its nearest neighbor pixels. And then, if an unreliable bit locates at any one of the 5 th ∼ 7 th bits of a pixel, it is adjusted with two nearest neighbors of the pixel, where the pixel is in-between these two nearest neighbors. Finally, for other unreliable bits, each one is approximated by the maximum and minimum possible values of nearest neighbors of its pixel. We conduct experiments for illustrating the efficiency, and demonstrate that the proposed algorithm can recover the embedded images with good visual quality from corrupted stego-images.

show abstract

Deep CNN for removal of salt and pepper noise

Cited by 27 publications

References 27 publications

Noise Reduction on Bracketed Images for High Dynamic Range Imaging

Noise Reduction on Bracketed Images for High Dynamic Range Imaging

Image Impulse Noise Removal Using Cascaded Filtering Based on Overlapped Adaptive Gaussian Smoothing and Convolutional Refinement Networks

Noise Removal in Embedded Image With Bit Approximation

Contact Info

Product

Resources

About