Estimation of Body Mass Index from Photographs using Deep Convolutional Neural Networks

TL;DR

This study demonstrates that deep convolutional neural networks can accurately estimate Body Mass Index from silhouette images derived from photographs, addressing data limitations common in medical applications.

Contribution

The paper introduces a novel approach of using silhouette images with CNNs to estimate BMI, improving accuracy with limited medical data.

Findings

High correlation between estimated and actual BMI on unseen data

Silhouette images effectively reduce data complexity

Method shows promise for non-invasive health assessments

Abstract

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.