3D Face Differentiation from Digital Camera Images
Abstract
Consider https://www.w3.org/1998/Math/MathML" display="inline"> g random objects (r.o.s) on a stratified space, https://www.w3.org/1998/Math/MathML" display="inline"> g ≥ 2. In order to perform a Fréchet MANOVA for the means of these r.o.s, one has to first check if there is any difference between the dimensions of the strata where these r.o.s live. A necessary condition for rejecting out of hand the equality is for a pair of these r.o.s to be on flat and convex connected components these strata of different dimensions. Once decided that the Fréchet means are inside the highest dimensional stratum, the MANOVA is reduced to a MANOVA on a manifold. In this chapter, we will therefore explore the theory necessary to run such Fréchet MANOVA, focusing on extrinsic MANOVA on a manifold.
Fields of Study & Subjects
Face recognition and analysis
Face and Expression Recognition
Topological and Geometric Data Analysis
Publication details
- Journal / source
- Chapman & Hall/CRC eBooks
- Pages
- 147–162
- Publication date
- 25 February 2026
- Language
- EN
- Document type
- Book chapter