Visual-attention-based thumbnail using two-stage GrabCut

Keisuke Arai, Hiromasa Takei, Hayato Yamana

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    This paper proposes a new thumbnail generation method to improve the recognizability of visual attention objects on small displays. Previous methods such as simple scaling reduce the recognizability of original images because the visual attention objects become too small to recognize. When we view thumbnails on small displays such as those of mobile devices, recognizability is indispensable for handling many images simultaneously. To solve the problem of low recognizability of visual attention objects, we adopt GrabCut to extract visual attention objects from an original image and then divide the original image into visual attention objects and a background image. While the background image is reduced to fit the size of a thumbnail, the extracted visual attention objects are merged into the reduced background image to preserve their recognizability. In adopting GrabCut, we propose a two-stage GrabCut method to automate the extraction of attention objects; the extraction was performed by hand in previous methods. Our experimental results show that our proposed method is able to shorten the search time by 44% and improve the precision of the search by 19% in comparison with simple scaling.

    Original languageEnglish
    Title of host publicationProceedings of 2012 International Conference on Multimedia Computing and Systems, ICMCS 2012
    Pages96-101
    Number of pages6
    DOIs
    Publication statusPublished - 2012
    Event2012 International Conference on Multimedia Computing and Systems, ICMCS 2012 - Tangiers
    Duration: 2012 May 102012 May 12

    Other

    Other2012 International Conference on Multimedia Computing and Systems, ICMCS 2012
    CityTangiers
    Period12/5/1012/5/12

    Fingerprint

    Display devices
    Mobile devices

    Keywords

    • content-aware image resizing
    • GrabCut
    • seam carving
    • small-size displays
    • thumbnail

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Human-Computer Interaction
    • Software

    Cite this

    Arai, K., Takei, H., & Yamana, H. (2012). Visual-attention-based thumbnail using two-stage GrabCut. In Proceedings of 2012 International Conference on Multimedia Computing and Systems, ICMCS 2012 (pp. 96-101). [6320153] https://doi.org/10.1109/ICMCS.2012.6320153

    Visual-attention-based thumbnail using two-stage GrabCut. / Arai, Keisuke; Takei, Hiromasa; Yamana, Hayato.

    Proceedings of 2012 International Conference on Multimedia Computing and Systems, ICMCS 2012. 2012. p. 96-101 6320153.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Arai, K, Takei, H & Yamana, H 2012, Visual-attention-based thumbnail using two-stage GrabCut. in Proceedings of 2012 International Conference on Multimedia Computing and Systems, ICMCS 2012., 6320153, pp. 96-101, 2012 International Conference on Multimedia Computing and Systems, ICMCS 2012, Tangiers, 12/5/10. https://doi.org/10.1109/ICMCS.2012.6320153
    Arai K, Takei H, Yamana H. Visual-attention-based thumbnail using two-stage GrabCut. In Proceedings of 2012 International Conference on Multimedia Computing and Systems, ICMCS 2012. 2012. p. 96-101. 6320153 https://doi.org/10.1109/ICMCS.2012.6320153
    Arai, Keisuke ; Takei, Hiromasa ; Yamana, Hayato. / Visual-attention-based thumbnail using two-stage GrabCut. Proceedings of 2012 International Conference on Multimedia Computing and Systems, ICMCS 2012. 2012. pp. 96-101
    @inproceedings{441e92b73c9f429aa22fdf8562dd06d6,
    title = "Visual-attention-based thumbnail using two-stage GrabCut",
    abstract = "This paper proposes a new thumbnail generation method to improve the recognizability of visual attention objects on small displays. Previous methods such as simple scaling reduce the recognizability of original images because the visual attention objects become too small to recognize. When we view thumbnails on small displays such as those of mobile devices, recognizability is indispensable for handling many images simultaneously. To solve the problem of low recognizability of visual attention objects, we adopt GrabCut to extract visual attention objects from an original image and then divide the original image into visual attention objects and a background image. While the background image is reduced to fit the size of a thumbnail, the extracted visual attention objects are merged into the reduced background image to preserve their recognizability. In adopting GrabCut, we propose a two-stage GrabCut method to automate the extraction of attention objects; the extraction was performed by hand in previous methods. Our experimental results show that our proposed method is able to shorten the search time by 44{\%} and improve the precision of the search by 19{\%} in comparison with simple scaling.",
    keywords = "content-aware image resizing, GrabCut, seam carving, small-size displays, thumbnail",
    author = "Keisuke Arai and Hiromasa Takei and Hayato Yamana",
    year = "2012",
    doi = "10.1109/ICMCS.2012.6320153",
    language = "English",
    isbn = "9781467315203",
    pages = "96--101",
    booktitle = "Proceedings of 2012 International Conference on Multimedia Computing and Systems, ICMCS 2012",

    }

    TY - GEN

    T1 - Visual-attention-based thumbnail using two-stage GrabCut

    AU - Arai, Keisuke

    AU - Takei, Hiromasa

    AU - Yamana, Hayato

    PY - 2012

    Y1 - 2012

    N2 - This paper proposes a new thumbnail generation method to improve the recognizability of visual attention objects on small displays. Previous methods such as simple scaling reduce the recognizability of original images because the visual attention objects become too small to recognize. When we view thumbnails on small displays such as those of mobile devices, recognizability is indispensable for handling many images simultaneously. To solve the problem of low recognizability of visual attention objects, we adopt GrabCut to extract visual attention objects from an original image and then divide the original image into visual attention objects and a background image. While the background image is reduced to fit the size of a thumbnail, the extracted visual attention objects are merged into the reduced background image to preserve their recognizability. In adopting GrabCut, we propose a two-stage GrabCut method to automate the extraction of attention objects; the extraction was performed by hand in previous methods. Our experimental results show that our proposed method is able to shorten the search time by 44% and improve the precision of the search by 19% in comparison with simple scaling.

    AB - This paper proposes a new thumbnail generation method to improve the recognizability of visual attention objects on small displays. Previous methods such as simple scaling reduce the recognizability of original images because the visual attention objects become too small to recognize. When we view thumbnails on small displays such as those of mobile devices, recognizability is indispensable for handling many images simultaneously. To solve the problem of low recognizability of visual attention objects, we adopt GrabCut to extract visual attention objects from an original image and then divide the original image into visual attention objects and a background image. While the background image is reduced to fit the size of a thumbnail, the extracted visual attention objects are merged into the reduced background image to preserve their recognizability. In adopting GrabCut, we propose a two-stage GrabCut method to automate the extraction of attention objects; the extraction was performed by hand in previous methods. Our experimental results show that our proposed method is able to shorten the search time by 44% and improve the precision of the search by 19% in comparison with simple scaling.

    KW - content-aware image resizing

    KW - GrabCut

    KW - seam carving

    KW - small-size displays

    KW - thumbnail

    UR - http://www.scopus.com/inward/record.url?scp=84869784126&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84869784126&partnerID=8YFLogxK

    U2 - 10.1109/ICMCS.2012.6320153

    DO - 10.1109/ICMCS.2012.6320153

    M3 - Conference contribution

    AN - SCOPUS:84869784126

    SN - 9781467315203

    SP - 96

    EP - 101

    BT - Proceedings of 2012 International Conference on Multimedia Computing and Systems, ICMCS 2012

    ER -