Evaluation of Morphometric Matching for the Identification of Caucasian Faces from Blurred Images.

Abstract

The reliability of the morphometric matching method for identifying the blurred images of Caucasian faces was examined experimentally using a computer-assisted facial image identification system. For evaluating the match of the 3D and 2D facial images in the same person (a match), the 3D facial image obtained from 10 subjects was compared to the 2D oblique facial image of the same subject ten times, yielding 100 superimpositions. In the case of different persons (non-matching), the 3D facial images of 10 subjects were each compared to the 2D facial images of other 9 subjects, yielding 90 superimpositions. As a matching criterion, the sum of the values of the average perpendicular difference of the facial outlines and the average point-to-point difference between the corresponding landmarks was used (abbr.: average difference).   The range of the average difference was 3.6-6.3 mm for the matching person and 5.8-15.3 mm for non-matching persons, respectively. The average difference and percentage error at the FP/FN crossover point were 6.0 mm and 3.2 percent. In this experiment, it was concluded that the morphometric matching method would be applicable to the identification of blurred images of Caucasian faces.