Smart Recognition COVID-19 System to Predict Suspicious Persons Based on Face Features

Area of Science:

• Medical Imaging
• Computer-Aided Diagnosis
• Respiratory Medicine

Background:

• The global spread of coronavirus disease (COVID-19) necessitates rapid and effective screening methods.
• Airport environments require non-invasive tools to identify individuals with respiratory distress, a primary COVID-19 symptom.
• Current screening methods may not adequately capture subtle respiratory anomalies.

Purpose of the Study:

• To develop a Computer-Aided Diagnosis (CAD) framework for predicting COVID-19 suspicion.
• To identify individuals exhibiting shortness of breath, a critical indicator of COVID-19.
• To propose a novel method for extracting respiratory anomalies from facial video analysis.

Main Methods:

• Development of a Smart Recognition COVID-19 (SRC) system.
• Utilizing face-based video analysis to estimate heart rate.
• Deriving a breath score to quantify respiratory status.

Main Results:

• The SRC system accurately estimates breath rate with an average error of approximately 1 breath per minute.
• The system successfully extracts shortness of breath anomalies from video data.
• Achieved a high degree of accuracy in breath score estimation.

Conclusions:

• The proposed SRC system offers a valuable tool for airport authorities to predict potentially infected passengers.
• This non-invasive approach aids in early identification of individuals with respiratory compromise.
• The technology supports public health measures by facilitating targeted screening in high-traffic areas.