Facial skin temperature is a physiological index that varies with skin blood flow controlled by autonomic nervous system activity. The facial skin temperature can be remotely measured using infrared thermography, and it has recently attracted attention as a remote biomarker. For example, studies have been reported to estimate human emotions, drowsiness, and mental stress on facial skin temperature. However, it is impossible to make a machine that can discriminate all infinite physiological and psychological states. Considering the practicality of skin temperature, a machine that can determine the normal state of facial skin temperature may be sufficient. In this study, we propose a completely new approach to incorporate the concept of anomaly detection into the analysis of physiological and psychological states by facial skin temperature. In this paper, the method for separating normal and anomaly facial thermal images using an anomaly detection model was investigated to evaluate the applicability of variational autoencoder (VAE) to facial thermal images.
The evaluation of physiological and psychological states using thermal infrared images is based on the skin temperature of specific regions of interest, such as the nose, mouth, and cheeks. To extract the skin temperature of the region of interest, face alignment in thermal infrared images is necessary. To date, the Active Appearance Model (AAM) has been used for face alignment in thermal infrared images. However, computation using this method is costly, and it has a low real-time performance. Conversely, face alignment of visible images using Cascaded Shape Regression (CSR) has been reported to have high real-time performance. However, no studies have been reported on face alignment in thermal infrared images using CSR. Therefore, the objective of this study was to verify the speed and robustness of face alignment in thermal infrared images using CSR. The results suggest that face alignment using CSR is more robust and computationally faster than AAM.
The increasing number of people with hypertension worldwide has become a matter of grave concern. Blood pressure monitoring using a non-contact measurement technique is expected to detect and control this medical condition. Previous studies have estimated blood pressure variations following an acute stress response based on facial thermal images obtained from infrared thermography devices. However, a non-contact resting blood pressure estimation method is required because blood pressure is generally measured in the resting state without inducing acute stress. Day-long blood pressure variations include short-term variations due to acute stress and long-term variations in circadian rhythms. The aim of this study is to estimate resting blood pressure from facial thermal images by separating and excluding short-term variations related to acute stress. To achieve this, short-term blood pressure variations components related to acute stress on facial thermal images were separated using independent component analysis. Resting blood pressure was estimated with the extracted independent components excluding the short-term components using multiple regression analysis. The results show that the proposed approach can accurately estimate resting blood pressure from facial thermal images, with a 9.90 mmHg root mean square error. In addition, features related to resting blood pressure were represented in the nose, lip, and cheek regions.
Human–computer interaction (HCI) is an interaction for mutual communication between humans and computers. HCI needs to recognize the human state quantitatively and in real-time. Although it is possible to quantitatively evaluate the human condition by measuring biological signals, the challenge is that it often requires physical constraints. There is an increasing interest in a non-contact method of estimating physiological and psychological states by measuring facial skin temperature using infrared thermography. However, due to individual differences in face shape, the accuracy of physiological and psychological state estimation using facial thermal images was sometimes low. To solve this problem, we hypothesized that spatial normalization of facial thermal image (SN-FTI) could reduce the effect of individual differences in facial shape. The objective of this study is to develop a method for SN-FTI and to evaluate the effect of SN-FTI on the estimation of physiological and psychological states. First, we attempted spatial normalization using facial features. The results suggested that SN-FTI would result in the same face shape among individuals. Since there are individual differences in facial skin temperature distribution, the inter-individual correlation coefficient is suggested to be lower than the intra-individual correlation coefficient. Next, we modeled the estimated drowsiness level using SN-FTIs and compared it with Normal. The results showed that SN-FTI slightly improved the discrimination rate of drowsiness level. SN-FTIs were suggested to reduce the effect of individual differences in facial structure on the estimation of physiological and psychological states.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.