Logo des Repositoriums

Auflistung nach Schlagwort "Ethnicity"

1 - 2 von 2
  • Konferenzbeitrag
    Investigating the impact of demographic factors on contactless fingerprint interoperability
    (BIOSIG 2022, 2022) Aeddon Berti, Nasser Nasrabadi and Jeremy Dawson
    Contactless fingerprints have continued to grow interoperability as a faster and more convenient replacement for contact fingerprints, and with covid-19 now starting to be a past event the need for hygienic alternatives has only grown after the sudden focus during the pandemic. Though, past works have shown issues with the interoperability of contactless prints from both kiosk devices and phone fingerprint collection apps. The focus of the paper is the evaluation of match performance between contact and contactless fingerprints, and the evaluation of match score bias based on skin demographics. AUC results indicate contactless match performance is as good as contact fingerprints, while phone contactless fingerprints fall short. Additionally, bias found for melanin showed specific ranges effected in both low melanin values and high melanin values.
  • Konferenzbeitrag
    Soft-Biometrics Estimation In the Era of Facial Masks
    (BIOSIG 2020 - Proceedings of the 19th International Conference of the Biometrics Special Interest Group, 2020) Alonso-Fernandez, Fernando; Diaz, Kevin Hernandez; Ramis, Silvia; Perales, Francisco J.; Bigun, Josef
    We analyze the use of images from face parts to estimate soft-biometrics indicators. Partial face occlusion is common in unconstrained scenarios, and it has become mainstream during the COVID-19 pandemic due to the use of masks. Here, we apply existing pre-trained CNN architectures, proposed in the context of the ImageNet Large Scale Visual Recognition Challenge, to the tasks of gender, age, and ethnicity estimation. Experiments are done with 12007 images from the Labeled Faces in the Wild (LFW) database. We show that such off-the-shelf features can effectively estimate soft-biometrics indicators using only the ocular region. For completeness, we also evaluate images showing only the mouth region. In overall terms, the network providing the best accuracy only suffers accuracy drops of 2-4% when using the ocular region, in comparison to using the entire face. Our approach is also shown to outperform in several tasks two commercial off-the-shelf systems (COTS) that employ the whole face, even if we only use the eye or mouth regions.