Facial Landmark based BMI Analysis for Pervasive Health Informatics

Body Mass Index (BMI), calculated based on the ratio between a person's height and weight, is a widely used metric for body weight or fatness. In this paper, we investigate the potential of face image-based BMI estimation using an RGB camera. We proposed a simple yet highly reproducible image processing framework that converts an input face image into a BMI value or obesity class (underweight, normal and overweight). In this framework, we explored the options of using 2D or 3D facial landmark models, view angle correction in 2D and 3D, different choices for facial feature extraction (landmark distances or coordinates), and different prediction models (regression or classification) based on shallow machine learning techniques. Our framework was thoroughly validated on two public datasets. The insights of this measurement are discussed, as well as the challenges and limitations, to increase the understanding for future improvement of camera-based BMI estimation. The source code of this study is available at https://github.com/hxfj/Facial-Landmark-based-BMI-Analysis.git.Clinical relevance- This contributes to simpler and more effective daily health management.