Predicting human body dimensions from single images: A first step in automatic malnutrition detection
Mohammedkhan,Hezha Balvert,Marleen Güven,Çiçek Postma,Eric
Mohammedkhan,Hezha
Balvert,Marleen
Güven,Çiçek
Postma,Eric
Abstract
Malnutrition in children accounts for 45% of child deaths globally. Automatic mal-nutrition 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
Description
Date
2021-11
Journal Title
Journal ISSN
Volume Title
Publisher
EAI
Research Projects
Organizational Units
Journal Issue
Keywords
SDG 2 - Zero Hunger
Citation
Mohammedkhan, H, Balvert, M, Güven, Ç & Postma, E 2021, Predicting human body dimensions from single images: A first step in automatic malnutrition detection. in Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI. EAI, INTERNATIONAL CONFERENCE ON AI for People: Towards Sustainable AI, 20/11/21. < https://aiforpeople.org/conference/assets/papers/CAIP21-P06.pdf >
License
info:eu-repo/semantics/restrictedAccess