We consider the problem of automatically learning color enhancements from a small set of sample color pairs, and then describing the enhancement by a three-dimensional look-up-table that can be stored and implemented as an ICC profile. We propose a new method for automatically learning a neighborhood for local statistical learning methods such as local linear regression, and show that this leads to relatively accurate descriptions of the desired color transformation and results in images that appear smooth and have natural depth of detail. In a previous work we showed that learning arbitrary color enhancements could result in colored specular highlights, causing images to look unnatural. We show that this can be solved by adding a null sample that maps white to white.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Custom color enhancements by statistical learning


    Beteiligte:
    Gupta, M.R. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    402183 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Custom Color Enhancements by Statistical Learning

    Gupta, M. R. | British Library Conference Proceedings | 2005


    Learning custom color transformations with adaptive neighborhoods

    Gupta, M.R. / Garcia, E.K. / Stroilov, A. | British Library Online Contents | 2008


    CUSTOM COLOR MATCHED TRANSPONDER RECEPTACLE

    STEIN MITCHELL | Europäisches Patentamt | 2016

    Freier Zugriff


    Automation Enhancements

    West, S. / SAE | British Library Conference Proceedings | 1998