EXTRACTION OF BIOMETRIC INFORMATION VIA VIDEO ANALYSIS USING MACHINE LEARNING : MEASUREMENT OF PALPEBRAL FISSURE HEIGHT AS AN EXAMPLE APPLICATION

DOI Web Site Open Access
  • NISHIMURA Eigo
    Graduate School of Design, Kyushu University
  • MOTOMURA Yuki
    Faculty of Design, Kyushu University National Institute of Mental Health: National Center of Neurology and Psychiatry
  • KATSUNUMA Ruri
    National Institute of Mental Health: National Center of Neurology and Psychiatry
  • YOSHIMURA Michitaka
    National Institute of Mental Health: National Center of Neurology and Psychiatry
  • MISHIMA Kazuo
    National Institute of Mental Health: National Center of Neurology and Psychiatry Department of Neuropsychiatry, Akita University Graduate School of Medicine
  • OGATA Yoshito
    Faculty of Design, Kyushu University

Bibliographic Information

Other Title
  • 機械学習を用いた動画解析による生体情報の自動追跡技術 ：瞼裂幅計測に用いた一例
  • キカイ ガクシュウ オ モチイタ ドウガ カイセキ ニ ヨル セイタイ ジョウホウ ノ ジドウ ツイセキ ギジュツ : マブタレツハバ ケイソク ニ モチイタ イチレイ

Search this article

Description

Methods of human motion tracking for acquiring biometric information are needed in order to apply knowledge of physiological anthropology. However, previous methods have difficulty in control of video shooting conditions. Thus, we developed a more robust motion tracking method using machine learning. In this report, we evaluated the accuracy of our method by comparing palpebral fissure height measured using manually selected data and tracking data obtained using YOLOv3. The results indicate that our method has practical accuracy in measuring palpebral fissure height and suggest that including noise in training data contributes to its accuracy.

Journal

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top