3DBODY.TECH 2018 - Paper 18.201

M. Carletti et al., "Estimating Body Fat from Depth Images: Hand-Crafted Features vs Convolutional Neural Networks", in Proc. of 3DBODY.TECH 2018 - 9th Int. Conf. and Exh. on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018, pp. 201-206, https://doi.org/10.15221/18.201.


Estimating Body Fat from Depth Images: Hand-Crafted Features vs Convolutional Neural Networks


Marco CARLETTI 1 Marco CRISTANI 1, Valentina CAVEDON 2, Chiara MILANESE 2, Carlo ZANCANARO 2, Andrea GIACHETTI 1

1 Dpt. of Computer Science, University of Verona, Verona, Italy;
2 Lab. of Anthropometry & Body Composition, Dpt. of Neurological and Movement Sciences, University of Verona, Verona, Italy


In this paper, we compare different approaches to estimate body fat percentages from simple depth images that can be captured by low-cost sensors. We implemented two frameworks, one based on hand-crafted features, using simple image processing methods to estimate directly from images a set of body measurements (e.g. areas, lengths girths), and one based on Convolutional Neural Networks, applying a direct regression from the grayscale maps representing the body depth, based on a pre-trained networks.
With these frameworks, we evaluated the fat percentage predictions obtained with the different methods on depth images of 350 subjects with known body composition estimated with a DXA scanner. Depth images were generated by extracting the z-buffer from the renderings of the 3D body scan models acquired on the group of subjects.
In our validation experiments, we evaluated the effect of different simulated acquisition setups, parameters settings, different image preprocessing and data-augmentation procedures and the addition of priors on height and weight on the prediction accuracy. Furthermore, since the dataset used is composed of professional sportsmen and a control group, we evaluated also the ability of both frameworks of predicting the sport practiced by the subjects with a cross-validation experiment.
In specific, we propose a customized ResNet50 regressor to evaluate the whole body fat percentage of the subjects directly from the depth acquisitions. Using the same input data, we also set up a neural classifier to predict the sport category of the athlets.
Despite the limited numbers of subjects and the restricted variability of body types (all males, Caucasian, with a small number of obese), the results obtained are promising and can be considered a first step towards the development of quick and cheap body fat estimation tools that can be extremely useful for sport, health and fitness applications.


Full paper: 18201carletti.pdf
Proceedings: 3DBODY.TECH 2018, 16-17 Oct. 2018, Lugano, Switzerland
Pages: 201-206
DOI: 10.15221/18.201

Copyright notice

© Hometrica Consulting - Dr. Nicola D'Apuzzo, Switzerland, www.hometrica.ch.
Reproduction of the proceedings or any parts thereof (excluding short quotations for the use in the preparation of reviews and technical and scientific papers) may be made only after obtaining the specific approval of the publisher. The papers appearing in the proceedings reflect the author's opinions. Their inclusion in these publications does not necessary constitute endorsement by the editor or by the publisher. Authors retain all rights to individual papers.

Proceedings of 3DBODY.TECH International Conferences on 3D Body Scanning & Processing Technologies, © Hometrica Consulting, Switzerland