A Classification Method of Normal and Overweight Females Based on Facial Features for Automated Medical Applications

Abstract

Obesity and overweight have become serious public health problems worldwide. Obesity and abdominal obesity are associated with type 2 diabetes, cardiovascular diseases, and metabolic syndrome. In this paper, we first suggest a method of predicting normal and overweight females according to body mass index (BMI) based on facial features. A total of 688 subjects participated in this study. We obtained the area under the ROC curve (AUC) value of 0.861 and kappa value of 0.521 in Female: 21–40 (females aged 21–40 years) group, and AUC value of 0.76 and kappa value of 0.401 in Female: 41–60 (females aged 41–60 years) group. In two groups, we found many features showing statistical differences between normal and overweight subjects by using an independent two-sample t-test. We demonstrated that it is possible to predict BMI status using facial characteristics. Our results provide useful information for studies of obesity and facial characteristics, and may provide useful clues in the development of applications for alternative diagnosis of obesity in remote healthcare.

BMI and WHR Are Reflected in Female Facial Shape and Texture: A Geometric Morphometric Image Analysis

“…Nutritional conditions are well known to affect the cheeks and the relative width of the lower face (see Wilkinson [1] for a review, Coetzee et al [2] in Caucasian and African faces, Lee et al [3] in Korean faces). Increasing BMI leads to a relative widening of the midface and lower face [3–5] as well as reduced eye height and a widening of the nose [3].…”

“…Increasing BMI leads to a relative widening of the midface and lower face [3–5] as well as reduced eye height and a widening of the nose [3]. Individuals with lower body fat proportion have a more angular face with relatively narrower cheeks and a pointed chin.…”

Body fat and facial shape are correlated in female adolescents

“…Tinlin et al (2013) replicated this finding in American women. There now is cross-cultural evidence that the cheeks and relative jaw width are the most affected by nutritional condition in terms of adult facial tissue depth (Wilkinson, 2004 for a review;Coetzee et al, 2010 in Caucasian and African faces, Lee et al, 2012 in Korean faces). The literature on adolescents is scarcer.…”

Face morphology: Can it tell us something about body weight and fat?

“…In [32,33] the study population is divided into four groups (by age and gender) and the waist circumference is used to classify each subject into two classes: normal and obese, defined with respect to the visceral obesity, assessed through the waist circumference. Hence, the predictive potential of the facial geometric features considered is evaluate in [33] by computing the AUC (area under the receiver operating characteristic curve) and the Cohen's Kappa, and such analysis shows that for each group there exist facial descriptors which are good in discriminating the two classes.…”

“…In adults, Lee et al proposed in [32] a prediction method of normal and overweight females based on BMI using geometrical facial features only. The features, measured on 2D images, include Euclidean distances, angles and face areas defined by selected soft-tissue landmarks.…”