Abstract
To capture scientific evidence in elderly care, a user-defined facial expression sensing service was proposed in our previous study. Since the time-series data of feature values have been growing at a high rate as the measurement time increases, it may be difficult to find points of interest, especially for detecting changes from the elderly facial expression, such as many elderly people can only be shown in a micro facial expression due to facial wrinkles and aging. The purpose of this paper is to implement a method to efficiently find points of interest (PoI) from the facial feature time-series data of the elderly. In the proposed method, the concept of changing point detection into the analysis of feature values is incorporated by us, to automatically detect big fluctuations or changes in the trend in feature values and detect the moment when the subject’s facial expression changed significantly. Our key idea is to introduce the novel concept of composite feature value to achieve higher accuracy and apply change-point detection to it as well as to single feature values. Furthermore, the PoI finding results from the facial feature time-series data of young volunteers and the elderly are analyzed and evaluated. By the experiments, it is found that the proposed method is able to capture the moment of large facial movements even for people with micro facial expressions and obtain information that can be used as a clue to investigate their response to care.
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference41 articles.
1. Mainstreaming Gender and Aging in the SDGs;Okamura,2016
2. For Japan’s Economic Revitalization (No.26), H. Future Investment Strategy (2017)http://www.kantei.go.jp/jp/singi/keizaisaisei/dai26/siryou.pdf
3. Care-Needs Certification in the Long-Term Care Insurance System of Japan
4. Facial expressions;Ekman;Handb. Cogn. Emot.,1999
5. Universal facial expressions of emotion;Ekman,1997
Cited by
8 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献