An estimation system of psychological conditions based on a micro facial expression recognition method

2014 Fiscal Year Final Research Report

• Project/Area Number: 25870570
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Perceptual information processing; Kansei informatics
• Research Institution: Tokyo University of Agriculture and Technology (2014); Kagoshima University (2013)
• Principal Investigator: AKAGI Yasuhiro 東京農工大学, 工学(系)研究科(研究院), 特任准教授 (90451989)
• Project Period (FY): 2013-04-01 – 2015-03-31
• Keywords: 表情認識 / 微表情 / トラッキング / ３次元点群

Outline of Final Research Achievements

A method for recognizing a micro expression which is a small motion appearing on a　face by using a high density and high frame-rate 3D reconstruction method are developed. In order to verify the set of methods to identify the site of micro expression and its accuracy, as a simple recognition problem, vocalizing unknown words was assigned to be further analyzed mechanically. As a result, by using highly accurate data of the facial movement, we were able to identify feature parts that matches with the human mental state, and able to estimate at about 75% accuracy. On the other hand, if the accuracy of the face shape measurement was decreased by few 10mm and lower the frame rate to 20fps, recognition of the micro expression became troublesome.

Free Research Field

コンピュータビジョン