Research Article
Predicting Human Body Dimensions from Single Images: a first step in automatic malnutrition detection
@INPROCEEDINGS{10.4108/eai.20-11-2021.2314166, author={Hezha MohammedKhan and Marleen Balvert and Cicek Guven and Eric Postma}, title={Predicting Human Body Dimensions from Single Images: a first step in automatic malnutrition detection}, proceedings={Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI, CAIP 2021, 20-24 November 2021, Bologna, Italy}, publisher={EAI}, proceedings_a={CAIP}, year={2021}, month={12}, keywords={convolutional neural networks hunger malnutrition human body shape}, doi={10.4108/eai.20-11-2021.2314166} }- Hezha MohammedKhan
Marleen Balvert
Cicek Guven
Eric Postma
Year: 2021
Predicting Human Body Dimensions from Single Images: a first step in automatic malnutrition detection
CAIP
EAI
DOI: 10.4108/eai.20-11-2021.2314166
Abstract
Malnutrition in children accounts for 45% of child deaths globally. Automatic malnutrition detection from digital photos serves as a decision support tool for early detection of malnutrition in rural areas. We study the feasibility of estimating body-shape characteristics from images of human body shapes as a first step in automatic malnutrition detection. We generate multi-view images of male and female bodies from rendered digital 3D scans of human bodies. Using convolutional neural networks (CNNs), we estimated waist circumference and body height with a mean absolute error of 59 mm and 9 mm, respectively. The estimation error of waist circumference depends on viewpoint. We conclude that automatic malnutrition detection from single images seems feasible, provided one or more suitable viewpoints are used.