Boutros, FadiDamer, NaserFang, MeilingRaja, KiranKirchbuchner, FlorianKuijper, ArjanBrömme, ArslanBusch, ChristophDantcheva, AntitzaRaja, KiranRathgeb, ChristianUhl, Andreas2020-09-162020-09-162020978-3-88579-700-5https://dl.gi.de/handle/20.500.12116/34340Despite the wide use of deep neural network for periocular verification, achieving smaller deep learning models with high performance that can be deployed on low computational powered devices remains a challenge. In term of computation cost, we present in this paper a lightweight deep learning model with only 1.1m of trainable parameters, DenseNet-20, based on DenseNet architecture. Further, we present an approach to enhance the verification performance of DenseNet-20 via knowledge distillation. With the experiments on VISPI dataset captured with two different smartphones, iPhone and Nokia, we show that introducing knowledge distillation to DenseNet-20 training phase outperforms the same model trained without knowledge distillation where the Equal Error Rate (EER) reduces from 8.36% to 4.56% EER on iPhone data, from 5.33% to 4.64% EER on Nokia data, and from 20.98% to 15.54% EER on cross-smartphone data.enPeriocular recognitionSmartphone biometric verificationKnowledge distillation.Text/Conference Paper1617-5468