A Hybrid Model for Photographic Supra-Projection

Abstract

Photographic supra-projection (CS) comes under forensic process in which video shots or photographs of a missing person are compared against the skull that is found. By projecting both photographs on top of each other (or, even better, matching a scanned 3-D skull model against the face photo/video shot), the forensic anthropologist can try to ascertain whether it is the same person. The overall process is affected by inherent uncertainty, mostly because two objects of different nature (a face and a skull ) are involved. In this paper, we extended existing evolutionary-algorithm-based techniques to automatically superimpose the 3-D skull model and the 2-D face photo with the aim to overcome the limitations that are associated with the different sources of uncertainty, which are present in the problem. Three different approaches to handle the imprecision will be proposed: Viola- Jones Face Detection Framework, Canonical Correlation Analysis and Inverse Compositional Active Appearance Model.
DOI: 10.17762/ijritcc2321-8169.150762