Development of Automated Diagnosis of Schizophrenia by Analyzing Facial Images
Hiroshi Kobayashi*, Kohki Kikuchi**, Miyako Tazaki*** and Yoshibumi Nakane****
*Faculty of Engineering, Tokyo University of Science
**Faculty of Precision Engineering, Chiba Institute of Technology
***Faculty of Science, Tokyo University of Science
****School of Medicine, Nagasaki University
In response to the need for quantitative information in diagnosing psychiatric disorders, we have developed an automated interview, automated extraction of facial organs, and acquisition of quantitative diagnostic information. We tried to obtain quantitative data for diagnosis by analyzing facial expressions during automated interviews. We focus on the movement of the pupils and head and the correlation between them, i.e., we develop a method for automated measurement of time sequential movements for the position of the pupil in relation to the frontal view of the face. By calculating the correlation between them, we obtain quantitative information that enables us to diagnose, for example, whether a subject may be schizophrenically inclined.
Copyright© 2002 by Fuji Technology Press Ltd. and Japan Society of Mechanical Engineers. All right reserved.