Detecting Peculiar Facial Expressions for Unspecified Persons Based on Sparse Coding

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K12100
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Intelligent informatics
• Research Institution: Kyushu University
• Principal Investigator: Suzuki Einoshin 九州大学, システム情報科学研究院, 教授 (10251638)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 異常検知 / 転移学習 / 顔表情

Outline of Final Research Achievements

We have invented theories and a method for detecting peculiar facial expressions from unlabeled data of the target person and unlabeled data of other persons, implemented them as a computer system, and demonstrated their effectiveness on a benchmark data on painful facial expressions.
Moreover, we have invented a method for detecting fatigue, implemented the method as an integrated system, and demonstrated its effectiveness with experiments on 6 persons. In this method, an autonomous mobile robot with Kinect version 2 observes the target person, who makes spontaneous smiling expressions and normal expressions every 30 minutes.

Free Research Field

知能情報学