We present a novel framework to directly estimate body fat percentage from depth images of human subjects and to visually evaluate salient points of the body shape related to the fat distribution. For this purpose, we created a novel, publicly available dataset including front and back depth images of a set of subjects with specific features (active young men or professional sportsmen) with associated ground truth fat values estimated with dual-energy x-ray absorptiometry (DXA) scanning. These depth images were obtained with depth rendering of an available dataset of whole body scans, simulating low-cost depth sensor acquisitions. We customized a ResNet-50 regressor to estimate fat percentage values directly from the front/back scans, achieving promising accuracy (standard errors of estimate SEE less than 2.1 on the depth renderings and 2.5 on a small set of real depth scans). We also demonstrate that, using a custom perturbation-based procedure for analyzing deep networks, it is possible to highlight, on subjects' depth images, the specific body areas related to fat accumulation (typically neck, shoulders, hip, and abdomen) and those characterizing skinny subjects (chest and abdomen).

Analyzing body fat from depth images

Carletti, Marco;Cristani, Marco;Cavedon, Valentina;Milanese, Chiara;Zancanaro, Carlo;Giachetti, Andrea
2018

Abstract

We present a novel framework to directly estimate body fat percentage from depth images of human subjects and to visually evaluate salient points of the body shape related to the fat distribution. For this purpose, we created a novel, publicly available dataset including front and back depth images of a set of subjects with specific features (active young men or professional sportsmen) with associated ground truth fat values estimated with dual-energy x-ray absorptiometry (DXA) scanning. These depth images were obtained with depth rendering of an available dataset of whole body scans, simulating low-cost depth sensor acquisitions. We customized a ResNet-50 regressor to estimate fat percentage values directly from the front/back scans, achieving promising accuracy (standard errors of estimate SEE less than 2.1 on the depth renderings and 2.5 on a small set of real depth scans). We also demonstrate that, using a custom perturbation-based procedure for analyzing deep networks, it is possible to highlight, on subjects' depth images, the specific body areas related to fat accumulation (typically neck, shoulders, hip, and abdomen) and those characterizing skinny subjects (chest and abdomen).
978-1-5386-8425-2
biomedical application; fat estimation; neural networks; regression
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/988340
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact