Fig 1.
A. 3D-body model from 2D images. B. Key points to separate body segments.
Fig 2.
Body shape feature derives from front and side curves.
Table 1.
Procedures used in the support vector regression for the photographic estimation of body fat.
Table 2.
Sample characteristics.
Fig 3.
Correlations between predicted body fat from the photographs and dual-energy x-ray absorptiometry (DXA).
(A) and Bland-Altman plots of the absolute (B) and relative (C) differences between the two methods (horizontal lines represent the 95% confidence intervals) among adults.
Fig 4.
Correlations between predicted body fat from the photographs and dual-energy x-ray absorptiometry (DXA).
(A) and Bland-Altman plots of the absolute (B) and relative (C) differences between the two methods (horizontal lines represent the 95% confidence intervals) among children.
Table 3.
Correlations and concordance between DXA and estimated body fat.