In order to expand the application field of the non-local means algorithm and improve the performance of removing salt and pepper noise, this paper proposes a simple but effective non-local means method for removing salt and pepper noise. Firstly, this method uses a sliding window to identify noise points and uses local means or median filtering to initially remove noise. Secondly, the proposed non-local means filtering algorithm with adaptive parameter is used to perform secondary denoising. In this paper, the smoothing parameter is designed as a piecewise function based on the intensity level of salt and pepper noise. The experimental results on the public dataset show that the new filter balances the relationship between the denoising effect and the time-consuming, and achieves state-of-the-art (SOTA) effect. Moreover, the new filter can effectively restore the pixels of the contaminated image and preserve the texture details of the image. Through comparative experiments, the superiority of the new method is proved.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Simple but Effective Non-local Means Method For Salt and Pepper Noise Removal


    Beteiligte:
    Ma, Xinyue (Autor:in) / Liu, Shugang (Autor:in)


    Erscheinungsdatum :

    12.10.2022


    Format / Umfang :

    1575892 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    New decision-based trimmed median filter for high-density salt-and-pepper noise removal in images

    Vijaykumar, V.R. / Santhanamari, G. | British Library Online Contents | 2014


    Estimation of salt-pepper noise in images in wavelet domain

    Tianyi, L. / Minghui, W. / Tao, L. et al. | British Library Online Contents | 2012


    An Effective Filtering Algorithm for Image Salt-Pepper Noises Based on Cellular Automata

    Liu, Songtao / Chen, Hongquan / Yang, Shaoqing | IEEE | 2008