New algorithms for recovering highly corrupted images with impulse noise

Jourabloo, Amin; Feghahati, Amir H.; Jamzad, Mansour

doi:10.1016/j.scient.2012.07.016

Cited by 41 publications

(30 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our approach is motivated by the classic image de-X problems, such as image denoising and de-blurring [9,10,11,12]. In image de-noising, the corrupted image is regarded as a degradation from the additive noise, e.g., salt-and-pepper noise and white Gaussian noise.…”

Section: Introductionmentioning

confidence: 99%

Face De-spoofing: Anti-spoofing via Noise Modeling

Jourabloo

Liu

2018

Lecture Notes in Computer Science

231

162

View full text Add to dashboard Cite

Many prior face anti-spoofing works develop discriminative models for recognizing the subtle differences between live and spoof faces. Those approaches often regard the image as an indivisible unit, and process it holistically, without explicit modeling of the spoofing process. In this work, motivated by the noise modeling and denoising algorithms, we identify a new problem of face despoofing, for the purpose of anti-spoofing: inversely decomposing a spoof face into a spoof noise and a live face, and then utilizing the spoof noise for classification. A CNN architecture with proper constraints and supervisions is proposed to overcome the problem of having no ground truth for the decomposition. We evaluate the proposed method on multiple face anti-spoofing databases. The results show promising improvements due to our spoof noise modeling. Moreover, the estimated spoof noise provides a visualization which helps to understand the added spoof noise by each spoof medium.

show abstract

Section: Introductionmentioning

confidence: 99%

Face De-spoofing: Anti-spoofing via Noise Modeling

Jourabloo

Liu

2018

Lecture Notes in Computer Science

231

162

View full text Add to dashboard Cite

show abstract

“…In [28] the authors used the PSNR and the correlation, Srinivasan and Ebenezer in [5] measure the performance of the algorithm using the PSNR and the "image enhancement factor" (IEF), and in [29,30] together with the PSNR the performance of the proposed algorithms is measured using the "mean absolute error" (MAE). The structural similarity index measure (SSIM) is used also in [31].…”

Section: Simulation Resultsmentioning

confidence: 99%

High-density impulse noise removal using fuzzy mathematical morphology

González-Hidalgo¹,

Massanet²,

Mir³

et al. 2013

Proceedings of the 8th Conference of the European Society for Fuzzy Logic and Technology

View full text Add to dashboard Cite

This paper proposes a filtering method for highdensity impulse noise removal based on the fuzzy mathematical morphology using t-norms. The method is a two phased method. In the first phase, an impulse noise detector based on the fuzzy tophat transforms is used to identify pixels which are likely to be contaminated by noise. In the second phase, the image is restored using a specialized regularization method using fuzzy open-close or fuzzy close-open sequences applied only to those selected contaminated pixels and applying then a block smart erase algorithm. Experimental results show that the proposed algorithm presents a better performance in terms of edge preservation and noise suppression than other nonlinear filtering methods, including the presented in [1], in which this method is based on.

show abstract

“…In Decision-based Average or Median filter (DAM) [28] Combine the advantages of the [29] and adaptive median filter in order to achieve better result. DAM has a good trade-off between quantitative and qualitative properties of the recovered image and computation time.…”

Section: Weighted Median Filter (Wmf)mentioning

confidence: 99%

Removal of High Density Impulse Noise using Efficient Median Filter for Digital Image

Soni¹,

Rathor²

2015

IJCA

View full text Add to dashboard Cite

An Efficient Median Filter (EMF) algorithm for removal or enhancement of gray scale images are highly corrupted impulse noise is proposed in this paper. Noise in image are represent the pixel value 0's and 255's are ensures that black and white dot in image. In proposed algorithm take an image and select 3x3 size window and target or center pixel value check if its value is 0's or 255's then image is corrupted otherwise noise free image. If image is noisy and target pixels neighboring pixel value is between 0's and 255's then we replace pixel value with the median value and if target pixels neighboring pixel value is 0's or 255's then we replace pixel value with the mean value. Else increased the window size and again repeat this process until image is denoised. The proposed filter algorithm shows better simulation result as compare the existing algorithms. The simulation result shows better and efficient performance of PSNR and MSE and computation time.

show abstract

New algorithms for recovering highly corrupted images with impulse noise

Cited by 41 publications

References 12 publications

Face De-spoofing: Anti-spoofing via Noise Modeling

Face De-spoofing: Anti-spoofing via Noise Modeling

High-density impulse noise removal using fuzzy mathematical morphology

Removal of High Density Impulse Noise using Efficient Median Filter for Digital Image

Contact Info

Product

Resources

About