Autonomous Face Recognition Machine Using a Fourier Feature Set

TLDR: Fourier coefficients are demonstrated as a reliable feature set for face recognition, using the Autonomous Face Recognition Machine developed at AFIT over the past several years, and the Fourier transform portion of the system was examined and improved.

Abstract: : This thesis demonstrates Fourier coefficients as a reliable feature set for face recognition, using the Autonomous Face Recognition Machine developed at AFIT over the past several years. The Fourier transform portion of the system was examined and improved. The code was made more efficient. Two Fourier transform routines (a fast Fourier transform and a classical Fourier transform) were tested and compared. A voting scheme was incorporated for examining multiple looks at test faces. To further demonstrate performance, the number of faces in the data base was doubled. Recognition scores of up to 87% were achieved, compared to 63% for Sander's process with Fourier coefficients as a feature set and 67% for Lambert's process with a center-of-mass feature set. This thesis includes complete system documentation, to assist those doing further research in this area.