Iris Liveness Detection Using Multiple Deep Convolution Networks

In the recent decade, comprehensive research has been carried out in terms of promising biometrics modalities regarding humans’ physical features for person recognition. This work focuses on iris characteristics and traits identification liveness detection. study used five pre-trained networks, including VGG-16, Inceptionv3, Resnet50, Densenet121, EfficientNetB7, to recognize using transfer learning techniques. These models are compared three state-of-the-art biometric databases: LivDet-Iris 2015 dataset, IIITD contact ND Iris3D 2020 dataset. Validation accuracy, loss, precision, recall, f1-score, APCER (attack presentation classification error rate), NPCER (normal ACER (average rate) were evaluate performance all models. According observational data, these have a considerable ability their experience field recognition nanostructures within region. Using Iris 3D EfficeintNetB7 model achieved 99.97% accuracy. Experiments show that outperform other current variants.