Estimation of Body Mass Index from Photographs using Deep Convolutional Neural Networks
This work addresses a public health concern by providing a non-invasive method for BMI estimation, but it is incremental as it applies existing techniques to a medical domain with limited data.
The researchers tackled the problem of estimating Body Mass Index (BMI) from photographs using deep convolutional neural networks, achieving high correlation on unseen data in a study with 161 participants.
Obesity is an important concern in public health, and Body Mass Index is one of the useful (and proliferant) measures. We use Convolutional Neural Networks to determine Body Mass Index from photographs in a study with 161 participants. Low data, a common problem in medicine, is addressed by reducing the information in the photographs by generating silhouette images. Results present with high correlation when tested on unseen data.