Face recognition using the POEM descriptor

H...............H

Show simple item record

dc.contributor.author Vu, Ngoc-Son
dc.contributor.author Dee, Hannah Mary
dc.contributor.author Caplier, Alice
dc.date.accessioned 2012-03-13T12:14:47Z
dc.date.available 2012-03-13T12:14:47Z
dc.date.issued 2012-07
dc.identifier.citation Vu , N-S , Dee , H M & Caplier , A 2012 , ' Face recognition using the POEM descriptor ' Pattern Recognition , vol 45 , no. 7 , pp. 2478-2488 . , 10.1016/j.patcog.2011.12.021 en
dc.identifier.issn 0031-3203
dc.identifier.other PURE: 175292
dc.identifier.other dspace: 2160/7802
dc.identifier.uri http://hdl.handle.net/2160/7802
dc.description Vu, N-S., Dee, H. M., Caplier, A. (2012). Face recognition using the POEM descriptor. Pattern Recognition, 45 (7), 2478-2488 en
dc.description.abstract Real-world face recognition systems require careful balancing of three concerns: computational cost, robustness, and discriminative power. In this paper we describe a new descriptor, POEM (patterns of oriented edge magnitudes), by applying a self-similarity based structure on oriented magnitudes and prove that it addresses all three criteria. Experimental results on the FERET database show that POEM outperforms other descriptors when used with nearest neighbour classifiers. With the LFW database by combining POEM with GMMs and with multi-kernel SVMs, we achieve comparable results to the state of the art. Impressively, POEM is around 20 times faster than Gabor-based methods. en
dc.language.iso eng
dc.relation.ispartof Pattern Recognition en
dc.subject face recognition en
dc.subject face descriptors en
dc.subject FERET en
dc.subject LFW en
dc.title Face recognition using the POEM descriptor en
dc.type Text en
dc.type.publicationtype Article (Journal) en
dc.identifier.doi http://dx.doi.org/10.1016/j.patcog.2011.12.021
dc.contributor.institution Vision, Graphics and Visualisation Group en
dc.contributor.institution Department of Computer Science en
dc.description.status Peer reviewed en


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Cadair


Advanced Search

Browse

My Account