An image processing based method for chewing detection using Variable-intensity template

Atsuto Fujimoto, Takaaki Ohkawauchi, Junji Yamato, Jun Ohya

    Research output: Contribution to journalConference article

    Abstract

    To contribute to the actualization of the care worker assistance robot, this paper proposes a method for detecting whether the care receiver is chewing from the video sequence acquired by the camera that observes that receiver. The proposed method detects the receiver's face and areas for both cheeks and chin. After applying some normalization to the areas, chewing detection that uses a variable-intensity template is performed, where the template consists of shape models, interest points and intensity distribution model. A likelihood based on the variableintensity template is computed so that the receiver is judged whether the receiver is chewing. Experiments using seven subjects are conducted. As a result, the accuracy of chewing detection by the proposed method is 83%, which is quite promising.

    Original languageEnglish
    Pages (from-to)2791-2794
    Number of pages4
    JournalIS and T International Symposium on Electronic Imaging Science and Technology
    VolumePart F138660
    DOIs
    Publication statusPublished - 2018 Jan 1
    EventIntelligent Robotics and Industrial Applications using Computer Vision 2018, IRIACV 2018 - Burlingame, United States
    Duration: 2018 Jan 282018 Feb 1

    Fingerprint

    mastication
    Mastication
    image processing
    Image processing
    templates
    receivers
    robots
    chin
    Cameras
    Robots
    cameras
    Experiments

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Computer Science Applications
    • Human-Computer Interaction
    • Software
    • Electrical and Electronic Engineering
    • Atomic and Molecular Physics, and Optics

    Cite this

    An image processing based method for chewing detection using Variable-intensity template. / Fujimoto, Atsuto; Ohkawauchi, Takaaki; Yamato, Junji; Ohya, Jun.

    In: IS and T International Symposium on Electronic Imaging Science and Technology, Vol. Part F138660, 01.01.2018, p. 2791-2794.

    Research output: Contribution to journalConference article

    @article{563ad2104170456c83d21fb375505971,
    title = "An image processing based method for chewing detection using Variable-intensity template",
    abstract = "To contribute to the actualization of the care worker assistance robot, this paper proposes a method for detecting whether the care receiver is chewing from the video sequence acquired by the camera that observes that receiver. The proposed method detects the receiver's face and areas for both cheeks and chin. After applying some normalization to the areas, chewing detection that uses a variable-intensity template is performed, where the template consists of shape models, interest points and intensity distribution model. A likelihood based on the variableintensity template is computed so that the receiver is judged whether the receiver is chewing. Experiments using seven subjects are conducted. As a result, the accuracy of chewing detection by the proposed method is 83{\%}, which is quite promising.",
    author = "Atsuto Fujimoto and Takaaki Ohkawauchi and Junji Yamato and Jun Ohya",
    year = "2018",
    month = "1",
    day = "1",
    doi = "10.2352/ISSN.2470-1173.2018.09.IRIACV-237",
    language = "English",
    volume = "Part F138660",
    pages = "2791--2794",
    journal = "IS and T International Symposium on Electronic Imaging Science and Technology",
    issn = "2470-1173",

    }

    TY - JOUR

    T1 - An image processing based method for chewing detection using Variable-intensity template

    AU - Fujimoto, Atsuto

    AU - Ohkawauchi, Takaaki

    AU - Yamato, Junji

    AU - Ohya, Jun

    PY - 2018/1/1

    Y1 - 2018/1/1

    N2 - To contribute to the actualization of the care worker assistance robot, this paper proposes a method for detecting whether the care receiver is chewing from the video sequence acquired by the camera that observes that receiver. The proposed method detects the receiver's face and areas for both cheeks and chin. After applying some normalization to the areas, chewing detection that uses a variable-intensity template is performed, where the template consists of shape models, interest points and intensity distribution model. A likelihood based on the variableintensity template is computed so that the receiver is judged whether the receiver is chewing. Experiments using seven subjects are conducted. As a result, the accuracy of chewing detection by the proposed method is 83%, which is quite promising.

    AB - To contribute to the actualization of the care worker assistance robot, this paper proposes a method for detecting whether the care receiver is chewing from the video sequence acquired by the camera that observes that receiver. The proposed method detects the receiver's face and areas for both cheeks and chin. After applying some normalization to the areas, chewing detection that uses a variable-intensity template is performed, where the template consists of shape models, interest points and intensity distribution model. A likelihood based on the variableintensity template is computed so that the receiver is judged whether the receiver is chewing. Experiments using seven subjects are conducted. As a result, the accuracy of chewing detection by the proposed method is 83%, which is quite promising.

    UR - http://www.scopus.com/inward/record.url?scp=85052847036&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85052847036&partnerID=8YFLogxK

    U2 - 10.2352/ISSN.2470-1173.2018.09.IRIACV-237

    DO - 10.2352/ISSN.2470-1173.2018.09.IRIACV-237

    M3 - Conference article

    VL - Part F138660

    SP - 2791

    EP - 2794

    JO - IS and T International Symposium on Electronic Imaging Science and Technology

    JF - IS and T International Symposium on Electronic Imaging Science and Technology

    SN - 2470-1173

    ER -