<p>In recent years, the prevalence of hypertension has increased, making routine blood pressure monitoring crucial for early detection and prevention. Our research group focused on facial skin temperature, a cardiovascular indicator that can be remotely measured using infrared thermography. It has been studied for non-contact blood pressure estimation based on the spatial characteristics of captured thermal facial images (TFIs). Previous studies have estimated the resting blood pressure based on spatial features extracted by applying independent component analysis (ICA) to acquired TFIs. In practical applications, the use of low-resolution TFIs is considered cost-effective and advantageous for reducing the burden of data management owing to the smaller data volume. However, the reduced resolution could potentially result in the loss of critical information necessary for accurate blood pressure estimation. Therefore, it is essential to evaluate whether low-resolution TFIs can maintain sufficient estimation accuracy for practical implementation. In this study, we developed a resting blood pressure estimation model using low-resolution TFIs with a resolution of 160 <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="10015_2025_1062_Article_IEq1.gif" Format="GIF" Height="13" Rendition="HTML" Resolution="72" Type="Linedraw" Width="19" /> </InlineMediaObject> <EquationSource Format="TEX">$\times$</EquationSource> <EquationSource Format="MATHML"><math> <mo>×</mo> </math></EquationSource> </InlineEquation> 120 pixels. We compared its estimation accuracy with that of a conventional model employing higher-resolution TFIs (320 <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="10015_2025_1062_Article_IEq1.gif" Format="GIF" Height="13" Rendition="HTML" Resolution="72" Type="Linedraw" Width="19" /> </InlineMediaObject> <EquationSource Format="TEX">$\times$</EquationSource> <EquationSource Format="MATHML"><math> <mo>×</mo> </math></EquationSource> </InlineEquation> 256 pixels). Following the procedure used in the previous studies, ICA was applied to the TFIs, and a linear support vector regression (SVR) model was constructed using the weights of the selected independent components as input features achieving a root-mean-square error (RMSE) of 13.1 mmHg and a correlation coefficient (<i>r</i>) of 0.369.</p>

Resting blood pressure estimation from a low-resolution single thermal facial image

期刊论文
出版模式：

开放获取
发表日期：

2025年9月19日

查看全文

Hana Furudate,
Kent Nagumo,
Akio Nozawa

摘要

In recent years, the prevalence of hypertension has increased, making routine blood pressure monitoring crucial for early detection and prevention. Our research group focused on facial skin temperature, a cardiovascular indicator that can be remotely measured using infrared thermography. It has been studied for non-contact blood pressure estimation based on the spatial characteristics of captured thermal facial images (TFIs). Previous studies have estimated the resting blood pressure based on spatial features extracted by applying independent component analysis (ICA) to acquired TFIs. In practical applications, the use of low-resolution TFIs is considered cost-effective and advantageous for reducing the burden of data management owing to the smaller data volume. However, the reduced resolution could potentially result in the loss of critical information necessary for accurate blood pressure estimation. Therefore, it is essential to evaluate whether low-resolution TFIs can maintain sufficient estimation accuracy for practical implementation. In this study, we developed a resting blood pressure estimation model using low-resolution TFIs with a resolution of 160 $\times$ $\times$ 120 pixels. We compared its estimation accuracy with that of a conventional model employing higher-resolution TFIs (320 $\times$ $\times$ 256 pixels). Following the procedure used in the previous studies, ICA was applied to the TFIs, and a linear support vector regression (SVR) model was constructed using the weights of the selected independent components as input features achieving a root-mean-square error (RMSE) of 13.1 mmHg and a correlation coefficient (r) of 0.369.