Title :
Random Features Applied to Face Recognition
Author :
Vázquez, Roberto A. ; Sossa, Humberto
Author_Institution :
Centro de Investigation en Computacion-IPN, Mexico City
Abstract :
In this paper we show how a simplified version of a describing vector can be used to efficiently recognize complex objects. We describe how simplified vectors are randomly obtained from complete describing vectors and how these simplified versions can be used to recognize faces. We compare the efficiency of the proposal against PCA using several known distance classifiers with a benchmark of faces.
Keywords :
face recognition; feature extraction; image classification; face recognition; object classification; random features; Cities and towns; Computer science; Covariance matrix; Face recognition; Higher order statistics; Principal component analysis; Proposals; Random variables; Statistical distributions; Testing;
Conference_Titel :
Current Trends in Computer Science, 2007. ENC 2007. Eighth Mexican International Conference on
Conference_Location :
Michoacan
Print_ISBN :
978-0-7695-2899-1
DOI :
10.1109/ENC.2007.13