A learning-based super-resolution system consisting of training and synthesis processes is presented. In the proposed system, a multi-resolution wavelet approach is applied to carry out the robust synthesis of both the global geometric structure and the local high-frequency detailed features of a facial image. In the training process, the input image is transformed into a series of images of increasingly lower resolution using the Haar discrete wavelet transform (DWT). The images at each resolution level are divided into patches, which are then projected onto an eigenspace to derive the corresponding projection weight vectors. In the synthesis process, a low-resolution input image is divided into patches, which are then projected onto the same eigenspace as that used in the training process. Modeling the resulting projection weight vectors as a Markov network, the maximum a posteriori (MAP) estimation approach is then applied to identity the best-matching patches with which to reconstruct the image at a higher level of resolution. The experimental results demonstrate that the proposed reconstruction system yields better results than the bi-cubic spline interpolation method.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning-Based Super-Resolution System Using Single Facial Image and Multi-resolution Wavelet Synthesis


    Beteiligte:
    Yagi, Yasushi (Herausgeber:in) / Kang, Sing Bing (Herausgeber:in) / Kweon, In So (Herausgeber:in) / Zha, Hongbin (Herausgeber:in) / Lui, Shu-Fan (Autor:in) / Wu, Jin-Yi (Autor:in) / Mao, Hsi-Shu (Autor:in) / Lien, Jenn-Jier James (Autor:in)

    Kongress:

    Asian Conference on Computer Vision ; 2007 ; Tokyo, Japan November 18, 2007 - November 22, 2007


    Erschienen in:

    Computer Vision – ACCV 2007 ; Kapitel : 10 ; 96-105


    Erscheinungsdatum :

    2007-01-01


    Format / Umfang :

    10 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Learning ramp transformation for single image super-resolution

    Singh, A. / Ahuja, N. | British Library Online Contents | 2015


    Wavelet-Based Super-Resolution Reconstruction: Theory and Algorithm

    Ji, H. / Fermuller, C. | British Library Conference Proceedings | 2006


    Multi-attention Based Ultra Lightweight Image Super-Resolution

    Muqeet, Abdul / Hwang, Jiwon / Yang, Subin et al. | British Library Conference Proceedings | 2020


    Wavelet-Based Super-Resolution Reconstruction: Theory and Algorithm

    Ji, Hui / Fermüller, Cornelia | Springer Verlag | 2006

    Freier Zugriff

    Degradation Model Learning for Real-World Single Image Super-Resolution

    Xiao, Jin / Yong, Hongwei / Zhang, Lei | British Library Conference Proceedings | 2021