The effect of normal adult aging on standard PCA face recognition accuracy rates

摘要

The issue of face aging has not been explicitly focused upon in the research on face recognition (FR) systems. What has been introduced by a few researchers is the impact of a probe against a match of different acquisition dates; the time span between probe and match image acquisition has not historically been sufficiently large enough to fully explore the impacts of age-progression on performance rates. In this work, we address the impacts of age-progression, which includes both structural and texture changes, on the standard PCA FR algorithm. A face database designed specifically to address the issues of age-progression is used with the FERET database. This work examines why the PCA FR system, and possibly other appearance based FR systems, is diminished recognition rates.