Face classification via sparse approximation

Battini Sonmez E., Sankur B., VARLI S.

3rd European Workshop on Biometrics and Identity Management, BioID 2011, Brandenburg, Havel, Almanya, 8 - 10 Mart 2011, cilt.6583 LNCS, ss.168-179, (Tam Metin Bildiri) identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 6583 LNCS
  • Doi Numarası: 10.1007/978-3-642-19530-3_16
  • Basıldığı Şehir: Brandenburg, Havel
  • Basıldığı Ülke: Almanya
  • Sayfa Sayıları: ss.168-179
  • Anahtar Kelimeler: Face classification, Fisher classifier, sparse approximation
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

We address the problem of 2D face classification under adverse conditions. Faces are difficult to recognize since they are highly variable due to such factors as illumination, expression, pose, occlusion and resolution. We investigate the potential of a method where the face recognition problem is cast as a sparse approximation. The sparse approximation provides a significant amount of robustness beneficial in mitigating various adverse effects. The study is conducted experimentally using the Extended Yale Face B database and the results are compared against the Fisher classifier benchmark. © 2011 Springer-Verlag.