The important task of 2D image classification and segmentation is the extraction of the local geometrical features. The convolution neural network is the common approach last years in this field. Usually, the neighborhood of each pixel of the image is implemented to collect local geometrical information. The information for each pixel is stored in a matrix. Then, Convolutional Auto-Encoder (CAE) is utilized to extract the main geometrical features. In this paper, we propose a neural network based on CAE to solve the extraction of local geometrical features problem for noisy images. Computer simulation results are provided to illustrate the performance of the proposed method.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Convolutional auto-encoder to extract local features of 2D images


    Beteiligte:
    Tescher, Andrew G. (Herausgeber:in) / Ebrahimi, Touradj (Herausgeber:in) / Kober, Vitaly (Autor:in) / Voronin, Sergei (Autor:in) / Makovetskii, Artyom (Autor:in) / Zhernov, Dmitrii (Autor:in) / Voronin, Aleksei (Autor:in)

    Kongress:

    Applications of Digital Image Processing XLVI ; 2023 ; San Diego, California, United States


    Erschienen in:

    Proc. SPIE ; 12674


    Erscheinungsdatum :

    2023-10-04





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Traffic anomaly detection method based on graph convolutional neural network auto-encoder

    LI XIAOJIE / REN ZHIYU / SHI CANGHONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff




    Analysis of Triple Flame Features under Acoustic Oscillations by using a Deep Auto-Encoder

    Saito, Masanori / Motohashi, Kazunori / lezumi, Tetsuo et al. | TIBKAT | 2019