Publications:Cross-Spectral Biometric Recognition with Pretrained CNNs as Generic Feature Extractors

Revision as of 21:22, 10 October 2019 by Slawek (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Do not edit this section

Keep all hand-made modifications below

Title Cross-Spectral Biometric Recognition with Pretrained CNNs as Generic Feature Extractors
Author Kevin Hernandez-Diaz and Fernando Alonso-Fernandez and Josef Bigun
Year 2019
PublicationType Conference Paper
Conference Swedish Symposium on Image Analysis, SSBA, Gothenburg, Swede), March 19-20, 2019
Diva url
Abstract Periocular recognition has gained attention in the last years thanks to its high discrimination capabilities in less constraint scenarios than face or iris. In this paper we propose a method for periocular verification under different light spectra using CNN features with the particularity that the network has not been trained for this purpose. We use a ResNet-101 pretrained model for the ImageNet Large Scale Visual Recognition Challenge to extract features from the IIITD Multispectral Periocular Database. At each layer the features are compared using χ 2 distance and cosine similitude to carry on verification between images, achieving an improvement in the EER and accuracy at 1% FAR of up to 63.13% and 24.79% in comparison to previous works that employ the same database. In addition to this, we train a neural network to match the best CNN feature layer vector from each spectrum. With this procedure, we achieve improvements of up to 65% (EER) and 87% (accuracy at 1% FAR) in cross-spectral verification with respect to previous studies.