Study of recognizing multiple persons' complicated hand gestures from the video sequence acquired by a moving camera

Luo Dan, Jun Ohya

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

    Abstract

    Recognizing hand gestures from the video sequence acquired by a dynamic camera could be a useful interface between humans and mobile robots. We develop a state based approach to extract and recognize hand gestures from moving camera images. We improved Human-Following Local Coordinate (HFLC) System, a very simple and stable method for extracting hand motion trajectories, which is obtained from the located human face, body part and hand blob changing factor. Condensation algorithm and PCA-based algorithm was performed to recognize extracted hand trajectories. In last research, this Condensation Algorithm based method only applied for one person's hand gestures. In this paper, we propose a principal component analysis (PCA) based approach to improve the recognition accuracy. For further improvement, temporal changes in the observed hand area changing factor are utilized as new image features to be stored in the database after being analyzed by PCA. Every hand gesture trajectory in the database is classified into either one hand gesture categories, two hand gesture categories, or temporal changes in hand blob changes. We demonstrate the effectiveness of the proposed method by conducting experiments on 45 kinds of sign language based Japanese and American Sign Language gestures obtained from 5 people. Our experimental recognition results show better performance is obtained by PCA based approach than the Condensation algorithm based method.

    Original languageEnglish
    Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
    Volume7527
    DOIs
    Publication statusPublished - 2010
    EventHuman Vision and Electronic Imaging XV - San Jose, CA
    Duration: 2010 Jan 182010 Jan 21

    Other

    OtherHuman Vision and Electronic Imaging XV
    CitySan Jose, CA
    Period10/1/1810/1/21

    Fingerprint

    Gesture
    principal components analysis
    Principal component analysis
    Person
    Camera
    Cameras
    cameras
    Condensation
    condensation
    Trajectories
    trajectories
    Principal Component Analysis
    Sign Language
    Trajectory
    robots
    Mobile robots
    conduction
    Mobile Robot
    Face
    Experiments

    Keywords

    • Condensation Algorithm
    • Dynamic camera image
    • Hand gesture extraction
    • Hand gesture recognition
    • PCA

    ASJC Scopus subject areas

    • Applied Mathematics
    • Computer Science Applications
    • Electrical and Electronic Engineering
    • Electronic, Optical and Magnetic Materials
    • Condensed Matter Physics

    Cite this

    Dan, L., & Ohya, J. (2010). Study of recognizing multiple persons' complicated hand gestures from the video sequence acquired by a moving camera. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 7527). [75271N] https://doi.org/10.1117/12.838759

    Study of recognizing multiple persons' complicated hand gestures from the video sequence acquired by a moving camera. / Dan, Luo; Ohya, Jun.

    Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7527 2010. 75271N.

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

    Dan, L & Ohya, J 2010, Study of recognizing multiple persons' complicated hand gestures from the video sequence acquired by a moving camera. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 7527, 75271N, Human Vision and Electronic Imaging XV, San Jose, CA, 10/1/18. https://doi.org/10.1117/12.838759
    Dan L, Ohya J. Study of recognizing multiple persons' complicated hand gestures from the video sequence acquired by a moving camera. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7527. 2010. 75271N https://doi.org/10.1117/12.838759
    Dan, Luo ; Ohya, Jun. / Study of recognizing multiple persons' complicated hand gestures from the video sequence acquired by a moving camera. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7527 2010.
    @inproceedings{93f8631af06e437bb5d298a356e34bc4,
    title = "Study of recognizing multiple persons' complicated hand gestures from the video sequence acquired by a moving camera",
    abstract = "Recognizing hand gestures from the video sequence acquired by a dynamic camera could be a useful interface between humans and mobile robots. We develop a state based approach to extract and recognize hand gestures from moving camera images. We improved Human-Following Local Coordinate (HFLC) System, a very simple and stable method for extracting hand motion trajectories, which is obtained from the located human face, body part and hand blob changing factor. Condensation algorithm and PCA-based algorithm was performed to recognize extracted hand trajectories. In last research, this Condensation Algorithm based method only applied for one person's hand gestures. In this paper, we propose a principal component analysis (PCA) based approach to improve the recognition accuracy. For further improvement, temporal changes in the observed hand area changing factor are utilized as new image features to be stored in the database after being analyzed by PCA. Every hand gesture trajectory in the database is classified into either one hand gesture categories, two hand gesture categories, or temporal changes in hand blob changes. We demonstrate the effectiveness of the proposed method by conducting experiments on 45 kinds of sign language based Japanese and American Sign Language gestures obtained from 5 people. Our experimental recognition results show better performance is obtained by PCA based approach than the Condensation algorithm based method.",
    keywords = "Condensation Algorithm, Dynamic camera image, Hand gesture extraction, Hand gesture recognition, PCA",
    author = "Luo Dan and Jun Ohya",
    year = "2010",
    doi = "10.1117/12.838759",
    language = "English",
    isbn = "9780819479204",
    volume = "7527",
    booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

    }

    TY - GEN

    T1 - Study of recognizing multiple persons' complicated hand gestures from the video sequence acquired by a moving camera

    AU - Dan, Luo

    AU - Ohya, Jun

    PY - 2010

    Y1 - 2010

    N2 - Recognizing hand gestures from the video sequence acquired by a dynamic camera could be a useful interface between humans and mobile robots. We develop a state based approach to extract and recognize hand gestures from moving camera images. We improved Human-Following Local Coordinate (HFLC) System, a very simple and stable method for extracting hand motion trajectories, which is obtained from the located human face, body part and hand blob changing factor. Condensation algorithm and PCA-based algorithm was performed to recognize extracted hand trajectories. In last research, this Condensation Algorithm based method only applied for one person's hand gestures. In this paper, we propose a principal component analysis (PCA) based approach to improve the recognition accuracy. For further improvement, temporal changes in the observed hand area changing factor are utilized as new image features to be stored in the database after being analyzed by PCA. Every hand gesture trajectory in the database is classified into either one hand gesture categories, two hand gesture categories, or temporal changes in hand blob changes. We demonstrate the effectiveness of the proposed method by conducting experiments on 45 kinds of sign language based Japanese and American Sign Language gestures obtained from 5 people. Our experimental recognition results show better performance is obtained by PCA based approach than the Condensation algorithm based method.

    AB - Recognizing hand gestures from the video sequence acquired by a dynamic camera could be a useful interface between humans and mobile robots. We develop a state based approach to extract and recognize hand gestures from moving camera images. We improved Human-Following Local Coordinate (HFLC) System, a very simple and stable method for extracting hand motion trajectories, which is obtained from the located human face, body part and hand blob changing factor. Condensation algorithm and PCA-based algorithm was performed to recognize extracted hand trajectories. In last research, this Condensation Algorithm based method only applied for one person's hand gestures. In this paper, we propose a principal component analysis (PCA) based approach to improve the recognition accuracy. For further improvement, temporal changes in the observed hand area changing factor are utilized as new image features to be stored in the database after being analyzed by PCA. Every hand gesture trajectory in the database is classified into either one hand gesture categories, two hand gesture categories, or temporal changes in hand blob changes. We demonstrate the effectiveness of the proposed method by conducting experiments on 45 kinds of sign language based Japanese and American Sign Language gestures obtained from 5 people. Our experimental recognition results show better performance is obtained by PCA based approach than the Condensation algorithm based method.

    KW - Condensation Algorithm

    KW - Dynamic camera image

    KW - Hand gesture extraction

    KW - Hand gesture recognition

    KW - PCA

    UR - http://www.scopus.com/inward/record.url?scp=77949461427&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77949461427&partnerID=8YFLogxK

    U2 - 10.1117/12.838759

    DO - 10.1117/12.838759

    M3 - Conference contribution

    SN - 9780819479204

    VL - 7527

    BT - Proceedings of SPIE - The International Society for Optical Engineering

    ER -