The search functionality is under construction.

The search functionality is under construction.

Image restoration based on Bayesian estimation in most previous studies has assumed that the noise accumulated in an image was independent for each pixel. However, when we take optical effects into account, it is reasonable to expect spatial correlation in the superimposed noise. In this paper, we discuss the restoration of images distorted by noise which is spatially correlated with translational symmetry in the realm of probabilistic processing. First, we assume that the original image can be produced by a Gaussian model based on only a nearest-neighbor effect and that the noise superimposed at each pixel is produced by a Gaussian model having spatial correlation characterized by translational symmetry. With this model, we can use Fourier transformation to calculate system characteristics such as the restoration error and also minimize the restoration error when the hyperparameters of the probabilistic model used in the restoration process coincides with those used in the formation process. We also discuss the characteristics of image restoration distorted by spatially correlated noise using a natural image. In addition, we estimate the hyperparameters using the maximum marginal likelihood and restore an image distorted by spatially correlated noise to evaluate this method of image restoration.

- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E92-A No.3 pp.853-861

- Publication Date
- 2009/03/01

- Publicized

- Online ISSN
- 1745-1337

- DOI
- 10.1587/transfun.E92.A.853

- Type of Manuscript
- PAPER

- Category
- Digital Signal Processing

The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.

Copy

Jun TSUZURUGI, Shigeru EIHO, "Image Restoration of the Natural Image under Spatially Correlated Noise" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 3, pp. 853-861, March 2009, doi: 10.1587/transfun.E92.A.853.

Abstract: Image restoration based on Bayesian estimation in most previous studies has assumed that the noise accumulated in an image was independent for each pixel. However, when we take optical effects into account, it is reasonable to expect spatial correlation in the superimposed noise. In this paper, we discuss the restoration of images distorted by noise which is spatially correlated with translational symmetry in the realm of probabilistic processing. First, we assume that the original image can be produced by a Gaussian model based on only a nearest-neighbor effect and that the noise superimposed at each pixel is produced by a Gaussian model having spatial correlation characterized by translational symmetry. With this model, we can use Fourier transformation to calculate system characteristics such as the restoration error and also minimize the restoration error when the hyperparameters of the probabilistic model used in the restoration process coincides with those used in the formation process. We also discuss the characteristics of image restoration distorted by spatially correlated noise using a natural image. In addition, we estimate the hyperparameters using the maximum marginal likelihood and restore an image distorted by spatially correlated noise to evaluate this method of image restoration.

URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.853/_p

Copy

@ARTICLE{e92-a_3_853,

author={Jun TSUZURUGI, Shigeru EIHO, },

journal={IEICE TRANSACTIONS on Fundamentals},

title={Image Restoration of the Natural Image under Spatially Correlated Noise},

year={2009},

volume={E92-A},

number={3},

pages={853-861},

abstract={Image restoration based on Bayesian estimation in most previous studies has assumed that the noise accumulated in an image was independent for each pixel. However, when we take optical effects into account, it is reasonable to expect spatial correlation in the superimposed noise. In this paper, we discuss the restoration of images distorted by noise which is spatially correlated with translational symmetry in the realm of probabilistic processing. First, we assume that the original image can be produced by a Gaussian model based on only a nearest-neighbor effect and that the noise superimposed at each pixel is produced by a Gaussian model having spatial correlation characterized by translational symmetry. With this model, we can use Fourier transformation to calculate system characteristics such as the restoration error and also minimize the restoration error when the hyperparameters of the probabilistic model used in the restoration process coincides with those used in the formation process. We also discuss the characteristics of image restoration distorted by spatially correlated noise using a natural image. In addition, we estimate the hyperparameters using the maximum marginal likelihood and restore an image distorted by spatially correlated noise to evaluate this method of image restoration.},

keywords={},

doi={10.1587/transfun.E92.A.853},

ISSN={1745-1337},

month={March},}

Copy

TY - JOUR

TI - Image Restoration of the Natural Image under Spatially Correlated Noise

T2 - IEICE TRANSACTIONS on Fundamentals

SP - 853

EP - 861

AU - Jun TSUZURUGI

AU - Shigeru EIHO

PY - 2009

DO - 10.1587/transfun.E92.A.853

JO - IEICE TRANSACTIONS on Fundamentals

SN - 1745-1337

VL - E92-A

IS - 3

JA - IEICE TRANSACTIONS on Fundamentals

Y1 - March 2009

AB - Image restoration based on Bayesian estimation in most previous studies has assumed that the noise accumulated in an image was independent for each pixel. However, when we take optical effects into account, it is reasonable to expect spatial correlation in the superimposed noise. In this paper, we discuss the restoration of images distorted by noise which is spatially correlated with translational symmetry in the realm of probabilistic processing. First, we assume that the original image can be produced by a Gaussian model based on only a nearest-neighbor effect and that the noise superimposed at each pixel is produced by a Gaussian model having spatial correlation characterized by translational symmetry. With this model, we can use Fourier transformation to calculate system characteristics such as the restoration error and also minimize the restoration error when the hyperparameters of the probabilistic model used in the restoration process coincides with those used in the formation process. We also discuss the characteristics of image restoration distorted by spatially correlated noise using a natural image. In addition, we estimate the hyperparameters using the maximum marginal likelihood and restore an image distorted by spatially correlated noise to evaluate this method of image restoration.

ER -