Robust Face Recognition in the Presence of Clutter

TitleRobust Face Recognition in the Presence of Clutter
Publication TypeBook Chapters
Year of Publication2003
AuthorsRajagopalan AN, Chellappa R, Koterba N
EditorKittler J, Nixon M
Book TitleAudio- and Video-Based Biometric Person AuthenticationAudio- and Video-Based Biometric Person Authentication
Series TitleLecture Notes in Computer Science
Pagination1062 - 1062
PublisherSpringer Berlin / Heidelberg
ISBN Number978-3-540-40302-9

We propose a new method within the framework of principal component analysis to robustly recognize faces in the presence of clutter. The traditional eigenface recognition method performs poorly when confronted with the more general task of recognizing faces appearing against a background. It misses faces completely or throws up many false alarms. We argue in favor of learning the distribution of background patterns and show how this can be done for a given test image. An eigenbackground space is constructed and this space in conjunction with the eigenface space is used to impart robustness in the presence of background. A suitable classifier is derived to distinguish non-face patterns from faces. When tested on real images, the performance of the proposed method is found to be quite good.