Blind Signal Processing of Facial Thermal Images based on Independent Component Analysis

Okamoto, Rikito; Bando, Shizuka; Nozawa, Akio

doi:10.1541/ieejeiss.136.1142

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the day-long variation in physiological indices includes short-term variations related to acute stress and long-term variations related to circadian rhythms. Applying ICA to FTIs can extract independent components related to specific psychophysiological responses [12]. Ito et al separated the components included in FTIs using ICA and extracted the core temperature or heart rate variable components related to circadian rhythms and acute stress [13].…”

Section: Introductionmentioning

confidence: 99%

Estimation of resting blood pressure using facial thermal images by separating acute stress variations

Iwashita

Nagumo

Oiwa

et al. 2021

Artif Life Robotics

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%