Synthetic Discriminant Function (SDF) formulation of correlation filters provides constraints for forming target subspaces for a target set. In this paper we extend the SDF formulation to include quadratic constraints and use this solution to form nonlinear manifolds in the target space. The theory for forming these manifolds will be developed and demonstrated with data.
Charles F. Hester,
Kelly K. D. Risko,
"Target manifold formation using a quadratic SDF", Proc. SPIE 8744, Automatic Target Recognition XXIII, 87440M (20 May 2013); doi: 10.1117/12.2015403; https://doi.org/10.1117/12.2015403