Images magnified by standard methods display a degradation of detail that is particularly noticeable in the blurry edges of text. Current super-resolution algorithms address the lack of sharpness by filling in the image with probable details. These algorithms break the outlines of text. Our novel algorithm for super-resolution of text magnifies images in real-time by interpolation with a variable linear filter. The coefficients of the filter are determined nonlinearly from the neighborhood to which it is applied. We train the mapping that defines the coefficients to specifically enhance edges of text, producing a conservative algorithm that infers the detail of magnified text. Possible applications include resizing web page layouts or other interfaces, and enhancing low resolution camera captures of text. In general, learning spatially-variable filters is applicable to other image filtering tasks.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning spatially-variable filters for super-resolution of text


    Contributors:


    Publication date :

    2005-01-01


    Size :

    188482 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learning Spatially-Variable Filters for Super-Resolution of Text

    Corduneanu, A. / Platt, J. C. | British Library Conference Proceedings | 2005



    Learning ramp transformation for single image super-resolution

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


    Learning-based super-resolution of 3D face model

    Shiqi Peng / Gang Pan / Zhaohui Wu | IEEE | 2005


    Image super-resolution via 2D tensor regression learning

    Yin, M. / Gao, J. / Cai, S. | British Library Online Contents | 2015