Background learning for robust face recognition with PCA in the presence of clutter

TitleBackground learning for robust face recognition with PCA in the presence of clutter
Publication TypeJournal Articles
Year of Publication2005
AuthorsRajagopalan AN, Chellappa R, Koterba NT
JournalImage Processing, IEEE Transactions on
Pagination832 - 843
Date Published2005/06//
ISBN Number1057-7149
KeywordsAutomated;Principal Component Analysis;Reproducibility of Results;Sensitivity and Specificity;Signal Processing, Biological;Models, Computer-Assisted;Information Storage and Retrieval;Models, Computer-Assisted;Subtraction Technique;, PCA;background learning;clutter;eigenface recognition method;face recognition;linear discriminant;principal component analysis;clutter;eigenvalues and eigenfunctions;face recognition;learning (artificial intelligence);principal component analysis;Algorith, Statistical;Pattern Recognition

We propose a new method within the framework of principal component analysis (PCA) to robustly recognize faces in the presence of clutter. The traditional eigenface recognition (EFR) method, which is based on PCA, works quite well when the input test patterns are faces. However, when confronted with the more general task of recognizing faces appearing against a background, the performance of the EFR method can be quite poor. It may miss faces completely or may wrongly associate many of the background image patterns to faces in the training set. In order to improve performance in the presence of background, 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 corresponding to the given test image and this space in conjunction with the eigenface space is used to impart robustness. A suitable classifier is derived to distinguish nonface patterns from faces. When tested on images depicting face recognition in real situations against cluttered background, the performance of the proposed method is quite good with fewer false alarms.