Modified total variation regularization using fuzzy complement for image denoising

Ahmed Ben Said, Sebti Foufou

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    In this paper, we propose a denoising algorithm based on the Total Variation (TV) model. Specifically, we associate to the regularization term of the Rodin-Osher-Fatimi (ROF) functional a small weight whenever denoising is performed in edge and texture regions, which means less regularization and more details preservation. On the other hand, a large weight is associated if the region being filtered is smooth which means noise will be well suppressed. The weight computation is inspired from the fuzzy edge complement. Experiments on well-known images and comparison with state of the art denoising algorithms demonstrate that the proposed method not only presents good denoising performance but also is able to preserve edge information.

    Original languageEnglish (US)
    Title of host publication2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015
    PublisherIEEE Computer Society
    Volume2016-November
    ISBN (Electronic)9781509003570
    DOIs
    StatePublished - Nov 28 2016
    Event2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015 - Auckland, New Zealand
    Duration: Nov 23 2015Nov 24 2015

    Other

    Other2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015
    CountryNew Zealand
    CityAuckland
    Period11/23/1511/24/15

    Fingerprint

    Image denoising
    Textures
    Experiments

    Keywords

    • denoising
    • edge detector
    • fuzzy complement
    • total variation

    ASJC Scopus subject areas

    • Computational Theory and Mathematics
    • Computer Vision and Pattern Recognition
    • Electrical and Electronic Engineering

    Cite this

    Said, A. B., & Foufou, S. (2016). Modified total variation regularization using fuzzy complement for image denoising. In 2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015 (Vol. 2016-November). [7761561] IEEE Computer Society. https://doi.org/10.1109/IVCNZ.2015.7761561

    Modified total variation regularization using fuzzy complement for image denoising. / Said, Ahmed Ben; Foufou, Sebti.

    2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015. Vol. 2016-November IEEE Computer Society, 2016. 7761561.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Said, AB & Foufou, S 2016, Modified total variation regularization using fuzzy complement for image denoising. in 2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015. vol. 2016-November, 7761561, IEEE Computer Society, 2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015, Auckland, New Zealand, 11/23/15. https://doi.org/10.1109/IVCNZ.2015.7761561
    Said AB, Foufou S. Modified total variation regularization using fuzzy complement for image denoising. In 2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015. Vol. 2016-November. IEEE Computer Society. 2016. 7761561 https://doi.org/10.1109/IVCNZ.2015.7761561
    Said, Ahmed Ben ; Foufou, Sebti. / Modified total variation regularization using fuzzy complement for image denoising. 2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015. Vol. 2016-November IEEE Computer Society, 2016.
    @inproceedings{9f6fd00fb2d6470cac1f1988d091822d,
    title = "Modified total variation regularization using fuzzy complement for image denoising",
    abstract = "In this paper, we propose a denoising algorithm based on the Total Variation (TV) model. Specifically, we associate to the regularization term of the Rodin-Osher-Fatimi (ROF) functional a small weight whenever denoising is performed in edge and texture regions, which means less regularization and more details preservation. On the other hand, a large weight is associated if the region being filtered is smooth which means noise will be well suppressed. The weight computation is inspired from the fuzzy edge complement. Experiments on well-known images and comparison with state of the art denoising algorithms demonstrate that the proposed method not only presents good denoising performance but also is able to preserve edge information.",
    keywords = "denoising, edge detector, fuzzy complement, total variation",
    author = "Said, {Ahmed Ben} and Sebti Foufou",
    year = "2016",
    month = "11",
    day = "28",
    doi = "10.1109/IVCNZ.2015.7761561",
    language = "English (US)",
    volume = "2016-November",
    booktitle = "2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - Modified total variation regularization using fuzzy complement for image denoising

    AU - Said, Ahmed Ben

    AU - Foufou, Sebti

    PY - 2016/11/28

    Y1 - 2016/11/28

    N2 - In this paper, we propose a denoising algorithm based on the Total Variation (TV) model. Specifically, we associate to the regularization term of the Rodin-Osher-Fatimi (ROF) functional a small weight whenever denoising is performed in edge and texture regions, which means less regularization and more details preservation. On the other hand, a large weight is associated if the region being filtered is smooth which means noise will be well suppressed. The weight computation is inspired from the fuzzy edge complement. Experiments on well-known images and comparison with state of the art denoising algorithms demonstrate that the proposed method not only presents good denoising performance but also is able to preserve edge information.

    AB - In this paper, we propose a denoising algorithm based on the Total Variation (TV) model. Specifically, we associate to the regularization term of the Rodin-Osher-Fatimi (ROF) functional a small weight whenever denoising is performed in edge and texture regions, which means less regularization and more details preservation. On the other hand, a large weight is associated if the region being filtered is smooth which means noise will be well suppressed. The weight computation is inspired from the fuzzy edge complement. Experiments on well-known images and comparison with state of the art denoising algorithms demonstrate that the proposed method not only presents good denoising performance but also is able to preserve edge information.

    KW - denoising

    KW - edge detector

    KW - fuzzy complement

    KW - total variation

    UR - http://www.scopus.com/inward/record.url?scp=85006920606&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85006920606&partnerID=8YFLogxK

    U2 - 10.1109/IVCNZ.2015.7761561

    DO - 10.1109/IVCNZ.2015.7761561

    M3 - Conference contribution

    VL - 2016-November

    BT - 2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015

    PB - IEEE Computer Society

    ER -