Face recognition using the POEM descriptor

Ngoc-Son Vu, Hannah Mary Dee, Alice Caplier

Research output: Contribution to journalArticlepeer-review

68 Citations (SciVal)


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.
Original languageEnglish
Pages (from-to)2478-2488
JournalPattern Recognition
Issue number7
Early online date08 Jan 2012
Publication statusPublished - Jul 2012


  • face recognition
  • face descriptors
  • LFW


Dive into the research topics of 'Face recognition using the POEM descriptor'. Together they form a unique fingerprint.

Cite this