Automatic Segmentation of Facial Regions of Interest and Stress Detection Using Machine Learning.

Stress is a factor that affects many people today and is responsible for many of the causes of poor quality of life. For this reason, it is necessary to be able to determine whether a person is stressed or not. Therefore, it is necessary to develop tools that are non-invasive, innocuous, and easy to use. This paper describes a methodology for classifying stress in humans by automatically detecting facial regions of interest in thermal images using machine learning during a short Trier Social Stress Test. Five regions of interest, namely the nose, right cheek, left cheek, forehead, and chin, are automatically detected. The temperature of each of these regions is then extracted and used as input to a classifier, specifically a Support Vector Machine, which outputs three states: baseline, stressed, and relaxed. The proposal was developed and tested on thermal images of 25 participants who were subjected to a stress-inducing protocol followed by relaxation techniques. After testing the developed methodology, an accuracy of 95.4% and an error rate of 4.5% were obtained. The methodology proposed in this study allows the automatic classification of a person's stress state based on a thermal image of the face. This represents an innovative tool applicable to specialists. Furthermore, due to its robustness, it is also suitable for online applications.

Face Thermal Map of the Mexican Population in the Basal State.

There has been a wide use of thermal images of the human body in recent years, specifically images with thermal information of regions of interest (ROI) in the face; this information can be used for epidemiological, clinical, and/or psychological purposes. Due to this, it is important to have plenty of information on temperature in these ROIs in the basal state that allows their use as a reference in terms of their thermal analysis. In this work, a face thermal map of the Mexican population in the basal state (n = 196) is created, adding the comparison between different population groups, such as gender, age, and clinical status, obtaining results of great interest for future research. The t-test for independent samples was applied to the ROIs with normal distribution and Mann−Whitney u-test to the ones that did not present normal distribution. Statistically significant differences were found in some of the ROI comparisons like the corrugator, the supraorbitals, and the chin between the control and clinical groups, as well as in the differentiation by age (p < 0.05).

Smart Sensor Based on Biofeedback to Measure Child Relaxation in Out-of-Home Care.

Children from out-of-home care are a vulnerable population that faces high stress and anxiety levels due to stressful experiences, such as being abused, being raped, and violence. This problem could have negative effects on their bio-psycho-social well-being if they are not provided with comprehensive psychological treatment. Numerous methods have been developed to help them relax, but there are no current approaches for assessing the relaxation level they reach. Based on this, a novel smart sensor that can evaluate the level of relaxation a child experiences is developed in this paper. It evaluates changes in thermal biomarkers (forehead, right and left cheek, chin, and maxillary) and heart rate (HR). Then, through a k-nearest neighbors (K-NN) intelligent classifier, four possible levels of relaxation can be obtained: no-relax, low-relax, relax, and very-relax. Additionally, an application (called i-CARE) for anxiety management, which is based on biofeedback diaphragmatic breathing, guided imagery, and video games, is evaluated. After testing the developed smart sensor, an 89.7% accuracy is obtained. The smart sensor used provides a reliable measurement of relaxation levels and the i-CARE application is effective for anxiety management, both of which are focused on children exposed to out-of-home care conditions.