TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Is Texture Denoising Efficiency Predictable?

Tutkimustuotosvertaisarvioitu

Standard

Is Texture Denoising Efficiency Predictable? / Rubel, Oleksii; Lukin, Vladimir; Abramov, Sergey; Vozel, Benoit; Pogrebnyak, Oleksiy; Egiazarian, Karen.

julkaisussa: International Journal of Pattern Recognition and Artificial Intelligence, Vuosikerta 32, Nro 1, 1860005 , 2018.

Tutkimustuotosvertaisarvioitu

Harvard

Rubel, O, Lukin, V, Abramov, S, Vozel, B, Pogrebnyak, O & Egiazarian, K 2018, 'Is Texture Denoising Efficiency Predictable?', International Journal of Pattern Recognition and Artificial Intelligence, Vuosikerta. 32, Nro 1, 1860005 . https://doi.org/10.1142/S0218001418600054

APA

Rubel, O., Lukin, V., Abramov, S., Vozel, B., Pogrebnyak, O., & Egiazarian, K. (2018). Is Texture Denoising Efficiency Predictable? International Journal of Pattern Recognition and Artificial Intelligence, 32(1), [1860005 ]. https://doi.org/10.1142/S0218001418600054

Vancouver

Rubel O, Lukin V, Abramov S, Vozel B, Pogrebnyak O, Egiazarian K. Is Texture Denoising Efficiency Predictable? International Journal of Pattern Recognition and Artificial Intelligence. 2018;32(1). 1860005 . https://doi.org/10.1142/S0218001418600054

Author

Rubel, Oleksii ; Lukin, Vladimir ; Abramov, Sergey ; Vozel, Benoit ; Pogrebnyak, Oleksiy ; Egiazarian, Karen. / Is Texture Denoising Efficiency Predictable?. Julkaisussa: International Journal of Pattern Recognition and Artificial Intelligence. 2018 ; Vuosikerta 32, Nro 1.

Bibtex - Lataa

@article{660ff3780336417ab86031d4206caf66,
title = "Is Texture Denoising Efficiency Predictable?",
abstract = "Images of different origin contain textures, and textural features in such regions are frequently employed in pattern recognition, image classification, information extraction, etc. Noise often present in analyzed images might prevent a proper solution of basic tasks in the aforementioned applications and is worth suppressing. This is not an easy task since even the most advanced denoising methods destroy texture in a more or less degree while removing noise. Thus, it is desirable to predict the filtering behavior before any denoising is applied. This paper studies the efficiency of texture image denoising for different noise intensities and several filter types under different visual quality criteria (quality metrics). It is demonstrated that the most efficient existing filters provide very similar results. From the obtained results, it is possible to generalize and employ the prediction strategy earlier proposed for denoising techniques based on the discrete cosine transform. Accuracy of such a prediction is studied and the ways to improve it are considered. Some practical recommendations concerning a decision to undertake whether it is worth applying a filter are given.",
keywords = "image processing, noise suppression, Texture denoising, visual quality",
author = "Oleksii Rubel and Vladimir Lukin and Sergey Abramov and Benoit Vozel and Oleksiy Pogrebnyak and Karen Egiazarian",
year = "2018",
doi = "10.1142/S0218001418600054",
language = "English",
volume = "32",
journal = "International Journal of Pattern Recognition and Artificial Intelligence",
issn = "0218-0014",
publisher = "World Scientific Publishing",
number = "1",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Is Texture Denoising Efficiency Predictable?

AU - Rubel, Oleksii

AU - Lukin, Vladimir

AU - Abramov, Sergey

AU - Vozel, Benoit

AU - Pogrebnyak, Oleksiy

AU - Egiazarian, Karen

PY - 2018

Y1 - 2018

N2 - Images of different origin contain textures, and textural features in such regions are frequently employed in pattern recognition, image classification, information extraction, etc. Noise often present in analyzed images might prevent a proper solution of basic tasks in the aforementioned applications and is worth suppressing. This is not an easy task since even the most advanced denoising methods destroy texture in a more or less degree while removing noise. Thus, it is desirable to predict the filtering behavior before any denoising is applied. This paper studies the efficiency of texture image denoising for different noise intensities and several filter types under different visual quality criteria (quality metrics). It is demonstrated that the most efficient existing filters provide very similar results. From the obtained results, it is possible to generalize and employ the prediction strategy earlier proposed for denoising techniques based on the discrete cosine transform. Accuracy of such a prediction is studied and the ways to improve it are considered. Some practical recommendations concerning a decision to undertake whether it is worth applying a filter are given.

AB - Images of different origin contain textures, and textural features in such regions are frequently employed in pattern recognition, image classification, information extraction, etc. Noise often present in analyzed images might prevent a proper solution of basic tasks in the aforementioned applications and is worth suppressing. This is not an easy task since even the most advanced denoising methods destroy texture in a more or less degree while removing noise. Thus, it is desirable to predict the filtering behavior before any denoising is applied. This paper studies the efficiency of texture image denoising for different noise intensities and several filter types under different visual quality criteria (quality metrics). It is demonstrated that the most efficient existing filters provide very similar results. From the obtained results, it is possible to generalize and employ the prediction strategy earlier proposed for denoising techniques based on the discrete cosine transform. Accuracy of such a prediction is studied and the ways to improve it are considered. Some practical recommendations concerning a decision to undertake whether it is worth applying a filter are given.

KW - image processing

KW - noise suppression

KW - Texture denoising

KW - visual quality

U2 - 10.1142/S0218001418600054

DO - 10.1142/S0218001418600054

M3 - Article

VL - 32

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

SN - 0218-0014

IS - 1

M1 - 1860005

ER -