Automatic Head Model Generation Based on Optimized Local Affine Transform Using Facial Range Scan Data

Akinobu Maejima, Shigeo Morishima

    Research output: Contribution to journalArticle

    Abstract

    We propose an automatic 3D human head modeling method using both a frontal facial image and geometry. In general, template mesh fitting methods are used to create a face model from a facial range data obtained by range scanner. However, previous fitting techniques need to manually specify markers to the scanned 3D geometry and to manually correct the 3D geometry of the missing parts that it is impossible to accurately measure the head geometry of the hair region. We therefore complement this region's 3D geometry with the template mesh's one. Our technique can generate the head model that the scanned 3D face geometry and the template mesh's one are seamlessly connected. The computational time of our method is much faster than previous template mesh fitting methods. We therefore conclude that proposed method is effective to create a large amount of head models in game and film industry and an entertainment system.

    Original languageEnglish
    Pages (from-to)404-413
    Number of pages10
    JournalJournal of the Institute of Image Electronics Engineers of Japan
    Volume38
    Issue number4
    DOIs
    Publication statusPublished - 2009

    Fingerprint

    Affine transforms
    Geometry

    Keywords

    • facial geometry importance weight
    • optimized local affine transform
    • template mesh fitting
    • universal kriging

    ASJC Scopus subject areas

    • Computer Science (miscellaneous)
    • Electrical and Electronic Engineering

    Cite this

    @article{3cc5b90d858a45b2a95857c6eddacd9b,
    title = "Automatic Head Model Generation Based on Optimized Local Affine Transform Using Facial Range Scan Data",
    abstract = "We propose an automatic 3D human head modeling method using both a frontal facial image and geometry. In general, template mesh fitting methods are used to create a face model from a facial range data obtained by range scanner. However, previous fitting techniques need to manually specify markers to the scanned 3D geometry and to manually correct the 3D geometry of the missing parts that it is impossible to accurately measure the head geometry of the hair region. We therefore complement this region's 3D geometry with the template mesh's one. Our technique can generate the head model that the scanned 3D face geometry and the template mesh's one are seamlessly connected. The computational time of our method is much faster than previous template mesh fitting methods. We therefore conclude that proposed method is effective to create a large amount of head models in game and film industry and an entertainment system.",
    keywords = "facial geometry importance weight, optimized local affine transform, template mesh fitting, universal kriging",
    author = "Akinobu Maejima and Shigeo Morishima",
    year = "2009",
    doi = "10.11371/iieej.38.404",
    language = "English",
    volume = "38",
    pages = "404--413",
    journal = "Journal of the Institute of Image Electronics Engineers of Japan",
    issn = "0285-9831",
    publisher = "Institute of Image Electronics Engineers of Japan",
    number = "4",

    }

    TY - JOUR

    T1 - Automatic Head Model Generation Based on Optimized Local Affine Transform Using Facial Range Scan Data

    AU - Maejima, Akinobu

    AU - Morishima, Shigeo

    PY - 2009

    Y1 - 2009

    N2 - We propose an automatic 3D human head modeling method using both a frontal facial image and geometry. In general, template mesh fitting methods are used to create a face model from a facial range data obtained by range scanner. However, previous fitting techniques need to manually specify markers to the scanned 3D geometry and to manually correct the 3D geometry of the missing parts that it is impossible to accurately measure the head geometry of the hair region. We therefore complement this region's 3D geometry with the template mesh's one. Our technique can generate the head model that the scanned 3D face geometry and the template mesh's one are seamlessly connected. The computational time of our method is much faster than previous template mesh fitting methods. We therefore conclude that proposed method is effective to create a large amount of head models in game and film industry and an entertainment system.

    AB - We propose an automatic 3D human head modeling method using both a frontal facial image and geometry. In general, template mesh fitting methods are used to create a face model from a facial range data obtained by range scanner. However, previous fitting techniques need to manually specify markers to the scanned 3D geometry and to manually correct the 3D geometry of the missing parts that it is impossible to accurately measure the head geometry of the hair region. We therefore complement this region's 3D geometry with the template mesh's one. Our technique can generate the head model that the scanned 3D face geometry and the template mesh's one are seamlessly connected. The computational time of our method is much faster than previous template mesh fitting methods. We therefore conclude that proposed method is effective to create a large amount of head models in game and film industry and an entertainment system.

    KW - facial geometry importance weight

    KW - optimized local affine transform

    KW - template mesh fitting

    KW - universal kriging

    UR - http://www.scopus.com/inward/record.url?scp=85024741991&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85024741991&partnerID=8YFLogxK

    U2 - 10.11371/iieej.38.404

    DO - 10.11371/iieej.38.404

    M3 - Article

    VL - 38

    SP - 404

    EP - 413

    JO - Journal of the Institute of Image Electronics Engineers of Japan

    JF - Journal of the Institute of Image Electronics Engineers of Japan

    SN - 0285-9831

    IS - 4

    ER -