Blind evaluation of additive noise variance in textured images by nonlinear processing of block DCT coefficients

Ponomarenko, Nikolay N.; Abramov, Sergey; Егиазарян, Карен; Astola, Jaakko

doi:10.1117/12.477717

Cited by 32 publications

(32 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We propose Ponomarenko's algorithm [41] available at IPOL webpage [42] to estimate the noise level. Finally, the algorithm tolerance is fixed to 10 −3 for the online demo.…”

Section: On Line Demomentioning

confidence: 99%

Chambolle's Projection Algorithm for Total Variation Denoising

Duran¹,

Coll²,

Sbert³

2013

Image Processing on Line

View full text Add to dashboard Cite

Denoising is the problem of removing the inherent noise from an image. The standard noise model is additive white Gaussian noise, where the observed image f is related to the underlying true image u by the degradation model f = u + η, and η is supposed to be at each pixel independently and identically distributed as a zero-mean Gaussian random variable. Since this is an ill-posed problem, Rudin, Osher and Fatemi introduced the total variation as a regularizing term. It has proved to be quite efficient for regularizing images without smoothing the boundaries of the objects. This paper focuses on the simple description of the theory and on the implementation of Chambolle's projection algorithm for minimizing the total variation of a grayscale image. Furthermore, we adapt the algorithm to the vectorial total variation for color images. The implementation is described in detail and its parameters are analyzed and varied to come up with a reliable implementation. Source CodeANSI C source code to produce the same results as the demo is accessible at the IPOL web page of this article 1 .

show abstract

“…We propose Ponomarenko's algorithm [41] available at IPOL webpage [42] to estimate the noise level. Finally, the algorithm tolerance is fixed to 10 −3 for the online demo.…”

Section: On Line Demomentioning

confidence: 99%

Chambolle's Projection Algorithm for Total Variation Denoising

Duran¹,

Coll²,

Sbert³

2013

Image Processing on Line

View full text Add to dashboard Cite

show abstract

“…Such a situation is typical, e.g., in image compression and filtering, automatic methods for noise variance estimation, etc. [1]. Note that nowadays such methods are mostly based on different orthogonal transforms [2].…”

Section: Introductionmentioning

confidence: 98%

“…Note that nowadays such methods are mostly based on different orthogonal transforms [2]. As a result, accurate description of distribution of spectral coefficients becomes the most important task [1,3,4].…”

Section: Introductionmentioning

confidence: 99%

Estimation of parameters for generalized Gaussian distribution

Roenko

Djurović²,

Simeunović

2014

2014 6th International Symposium on Communications, Control and Signal Processing (ISCCSP)

View full text Add to dashboard Cite

Shape parameter estimation procedures for generalized Gaussian distribution are considered. It is shown that the existing estimators can be divided into four groups: maximum likelihood algorithm; moment-based methods; entropy matching estimators and global convergence algorithm. Besides, properties of two recently introduced estimators of shape parameter are discussed. They are based on the combination of two procedures that use the evaluation of the fourth central moment and robust measure of kurtosis. Statistical properties of all considered estimators are investigated by means of defining their bias and variance values for samples of sizes 1000 and 4000 elements and shape parameter values ranging from 0.3 to 2.

show abstract

“…In particular, for σ 2 =200 one has T=25.12dB and for σ 2 =50 T=31.12dB. For real life images noise type and variance can be either known in advance or pre-estimated in a blind manner [27][28][29][30] . Then, for additive noise case, the parameter T is to be calculated as T=10log 10 (255 2 /σ 2 ) or by substituting the obtained estimate of variance instead of σ 2 .…”

Section: Approaches To Automatic Lossy Compression Of Noisy Imagesmentioning

confidence: 99%

“…Under some conditions, this can be done in an automatic manner on-board, and pre-filtering can be almost always performed automatically or with operator attraction at on-ground center before RS data archiving. On-board pre-filtering can be carried out, e.g., by using blind estimation of noise variance [28][29][30] and DCT-filter 31 with parameters set accordingly. In the case of on-ground pre-filtering, image pre-processing algorithm can be selected by operator with taking into account noise properties and the priorities of requirements to further processing (interpreting) 8 .…”

Section: Lossy Compression Of Pre-filtered Imagesmentioning

confidence: 99%

Quasi-optimal compression of noisy optical and radar images

et al. 2006

Self Cite

View full text Add to dashboard Cite

It is often necessary to compress remote sensing (RS) data such as optical or radar images. This is needed for transmitting them via communication channels from satellites and/or for storing in databases for later analysis of, for instance, scene temporal changes. Such images are generally corrupted by noise and this factor should be taken into account while selecting a data compression method and its characteristics, in the particular, compression ratio (CR). In opposite to the case of data transmission via communication channel when the channel capacity can be the crucial factor in selecting the CR, in the case of archiving original remote sensing images the CR can be selected using different criteria. The basic requirement could be to provide such a quality of the compressed images that will be appropriate for further use (interpreting) the images after decompression. In this paper we propose a blind approach to quasi-optimal compression of noisy optical and side look aperture radar images. It presumes that noise variance is either known a priori or pre-estimated using the corresponding automatic tools. Then, it is shown that it is possible (in an automatic manner) to set such a CR that produces an efficient noise reduction in the original images same time introducing minimal distortions to remote sensing data at compression stage. For radar images, it is desirable to apply a homomorphic transform before compression and the corresponding inverse transform after decompression. Real life examples confirming the efficiency of the proposed approach are presented.

show abstract

Blind evaluation of additive noise variance in textured images by nonlinear processing of block DCT coefficients

Cited by 32 publications

References 13 publications

Chambolle's Projection Algorithm for Total Variation Denoising

Chambolle's Projection Algorithm for Total Variation Denoising

Estimation of parameters for generalized Gaussian distribution

Quasi-optimal compression of noisy optical and radar images

Contact Info

Product

Resources

About