Thinning based Antialiasing Approach for Visual Saliency of Digital Images

O. Rukundo

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    Abstract

    A thinning based approach for spatial antialiasing (TAA) has been proposed for visual saliency of digital images. This TAA approach is based on edge-matting and digital compositing strategies. Prior to edgematting the image edges are detected using ant colony optimization (ACO) algorithm and then thinned using a fast parallel algorithm. After the edge-matting, a composite image is created between the edge-matted and non-antialiasing image. Motivations for adopting the ACO and fast parallel algorithm in lieu of others found in the literature are also extensively addressed in this paper. Preliminary TAA experimental outcomes are more promising but with debatable smoothness to some extent of the original size of the images in comparison.
    Original languageEnglish
    Title of host publicationInternational Conference on Computer Vision Theory and Applications (VISAPP 2015)
    PublisherSciTe Press
    Pages658-665
    Number of pages8
    ISBN (Electronic)9789897580895
    DOIs
    Publication statusPublished - 26 Mar 2015

    Fingerprint

    Ant colony optimization
    Parallel algorithms
    Composite materials

    Keywords

    • Antialiasing
    • ACO
    • Edge Detection
    • Thinning
    • Edge-matting
    • Compositing
    • Near-realism

    Cite this

    Rukundo, O. (2015). Thinning based Antialiasing Approach for Visual Saliency of Digital Images. In International Conference on Computer Vision Theory and Applications (VISAPP 2015) (pp. 658-665). SciTe Press. https://doi.org/10.5220/0005356206580665
    Rukundo, O. / Thinning based Antialiasing Approach for Visual Saliency of Digital Images. International Conference on Computer Vision Theory and Applications (VISAPP 2015). SciTe Press, 2015. pp. 658-665
    @inproceedings{393cbcfaa2114fdda39546bc14b5ebab,
    title = "Thinning based Antialiasing Approach for Visual Saliency of Digital Images",
    abstract = "A thinning based approach for spatial antialiasing (TAA) has been proposed for visual saliency of digital images. This TAA approach is based on edge-matting and digital compositing strategies. Prior to edgematting the image edges are detected using ant colony optimization (ACO) algorithm and then thinned using a fast parallel algorithm. After the edge-matting, a composite image is created between the edge-matted and non-antialiasing image. Motivations for adopting the ACO and fast parallel algorithm in lieu of others found in the literature are also extensively addressed in this paper. Preliminary TAA experimental outcomes are more promising but with debatable smoothness to some extent of the original size of the images in comparison.",
    keywords = "Antialiasing, ACO, Edge Detection, Thinning, Edge-matting, Compositing, Near-realism",
    author = "O. Rukundo",
    year = "2015",
    month = "3",
    day = "26",
    doi = "10.5220/0005356206580665",
    language = "English",
    pages = "658--665",
    booktitle = "International Conference on Computer Vision Theory and Applications (VISAPP 2015)",
    publisher = "SciTe Press",

    }

    Rukundo, O 2015, Thinning based Antialiasing Approach for Visual Saliency of Digital Images. in International Conference on Computer Vision Theory and Applications (VISAPP 2015). SciTe Press, pp. 658-665. https://doi.org/10.5220/0005356206580665

    Thinning based Antialiasing Approach for Visual Saliency of Digital Images. / Rukundo, O.

    International Conference on Computer Vision Theory and Applications (VISAPP 2015). SciTe Press, 2015. p. 658-665.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    TY - GEN

    T1 - Thinning based Antialiasing Approach for Visual Saliency of Digital Images

    AU - Rukundo, O.

    PY - 2015/3/26

    Y1 - 2015/3/26

    N2 - A thinning based approach for spatial antialiasing (TAA) has been proposed for visual saliency of digital images. This TAA approach is based on edge-matting and digital compositing strategies. Prior to edgematting the image edges are detected using ant colony optimization (ACO) algorithm and then thinned using a fast parallel algorithm. After the edge-matting, a composite image is created between the edge-matted and non-antialiasing image. Motivations for adopting the ACO and fast parallel algorithm in lieu of others found in the literature are also extensively addressed in this paper. Preliminary TAA experimental outcomes are more promising but with debatable smoothness to some extent of the original size of the images in comparison.

    AB - A thinning based approach for spatial antialiasing (TAA) has been proposed for visual saliency of digital images. This TAA approach is based on edge-matting and digital compositing strategies. Prior to edgematting the image edges are detected using ant colony optimization (ACO) algorithm and then thinned using a fast parallel algorithm. After the edge-matting, a composite image is created between the edge-matted and non-antialiasing image. Motivations for adopting the ACO and fast parallel algorithm in lieu of others found in the literature are also extensively addressed in this paper. Preliminary TAA experimental outcomes are more promising but with debatable smoothness to some extent of the original size of the images in comparison.

    KW - Antialiasing

    KW - ACO

    KW - Edge Detection

    KW - Thinning

    KW - Edge-matting

    KW - Compositing

    KW - Near-realism

    U2 - 10.5220/0005356206580665

    DO - 10.5220/0005356206580665

    M3 - Conference contribution

    SP - 658

    EP - 665

    BT - International Conference on Computer Vision Theory and Applications (VISAPP 2015)

    PB - SciTe Press

    ER -

    Rukundo O. Thinning based Antialiasing Approach for Visual Saliency of Digital Images. In International Conference on Computer Vision Theory and Applications (VISAPP 2015). SciTe Press. 2015. p. 658-665 https://doi.org/10.5220/0005356206580665