The assessment of anterior eye diseases and the understanding of psychological functions of blinking can benefit greatly from a validated blinking detection technology. In this work, we proposed an algorithm based on facial recognition built on current video processing technologies to automatically filter and analyze blinking movements. We compared electrooculography (EOG), the gold standard of blinking measurement, with manual video tape recording counting (mVTRc) and our proposed automated video tape recording analysis (aVTRa) in both static and dynamic conditions to validate our aVTRa method.
We measured blinking in both static condition, where the subject was sitting still with chin fixed on the table, and dynamic condition, where the subject's face was not fixed and natural communication was taking place between the subject and interviewer. We defined concordance of blinks between measurement methods as having less than 50 ms difference between eyes opening and closing.
The subjects consisted of seven healthy Japanese volunteers (3 male, four female) without significant eye disease with average age of 31.4±7.2. The concordance of EOG vs. aVTRa, EOG vs. mVTRc, and aVTRa vs. mVTRc (average±SD) were found to be 92.2±10.8%, 85.0±16.5%, and 99.6±1.0% in static conditions and 32.6±31.0%, 28.0±24.2%, and 98.5±2.7% in dynamic conditions, respectively.
In static conditions, we have found a high blink concordance rate between the proposed aVTRa versus EOG, and confirmed the validity of aVTRa in both static and dynamic conditions.
Department of Ophthalmology (M.K., M.Y., L.K.-C., K.T.), Keio University School of Medicine, Tokyo, Japan; RIKEN (M.K., S.W.), Center for Advanced Photonics, Wako, Saitama, Japan; Department of Psychiatry (M.K., M.M., T.K.), Keio University School of Medicine, Tokyo, Japan; and Department of Psychiatry (T.K.), Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Hempstead, New York, NY.
Address correspondence to Taishiro Kishimoto, M.D., Ph.D., Keio University School of Medicine, 35 Shinanomachi Shinjuku-ku, Tokyo, Japan 160-8582; e-mail: firstname.lastname@example.org
T. Kishimoto has received consultant fees from Dainippon Sumitomo, Novartis, and Otsuka, and has received speaker's honoraria from Banyu, Eli Lilly, Dainippon Sumitomo, Janssen, Novartis, Otsuka, and Pfizer, outside the submitted work. He has also received grant support from Tanabe-Mitsubishi, Dainippon Sumitomo, and Otsuka, outside the submitted work. Masaru Mimura has received grants and/or speaker's honoraria from Abbvie, Asahi Kasei, Astellas, Chugai, Cracie, Daiichi Sankyo, Dainippon Sumitomo, Eisai, Eli Lilly, Fuji Film, Janssen, Meiji Pharma, Mochida, MSD, Novartis, Ono, Otsuka, Pfizer, Shionogi, Takeda, and Yoshitomi Pharmaceutical within the past three years, outside the submitted work. K. Tsubota has no conflict of interest related to the contents of the work; however, outside the submitted work, he is a consultant for Santen Pharmaceutical Co., Ltd, Otsuka Pharmaceutical Co., Ltd, AMO Japan KK, Novaliq GmnH, MediProduct Inc., and NIDEK Co., Ltd, and holds patents or patents pending with Jins Co., Ltd, Kowa Comp, Tsubota Laboratory, Inc., and Echo Denki. The remaining authors have no conflict of interest to disclose.
Supported by the Japan Agency for Medical Research and Development [grant number 16929962].
M. Kitazawa and M. Yoshimura worked equally to contribute to the study.
Accepted March 12, 2018