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
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
Original language | English |
---|---|
Title of host publication | Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI |
Publisher | EAI |
Number of pages | 8 |
Publication status | Published - Nov 2021 |
Event | INTERNATIONAL CONFERENCE ON AI for People: Towards Sustainable AI - Online Duration: 20 Nov 2021 → 24 Nov 2021 https://aiforpeople.org/conference/ |
Conference
Conference | INTERNATIONAL CONFERENCE ON AI for People: Towards Sustainable AI |
---|---|
Abbreviated title | CAIP'21 |
Period | 20/11/21 → 24/11/21 |
Internet address |