A Novel Embedding Architecture and Score Level Fusion Scheme for Occluded Image Acquisition in Ear Biometrics System
Abstract: Significant progress in the field of ear-based biometrics has been made in recent studies. But methods to deal with degradation caused by hair occlusions during ear image acquisition have not been addressed yet. Use of occluded ear images from both sides can give better or comparable results to that of clean image acquisition from a single side. To test this, in this work we introduce a novel embedding generation network using conventional CNNs along with parallel paths of Learnable Scattering Wavelet Networks. We have shown results of experiments for augmented training of proposed embedding network and score level fusion of both side-ear images to mitigate the effects of hair occlusions in verification and identification tasks. We also show extensive simulation results over closed and open testing sets to analyse the one-shot learning capabilities of our proposed embedding network. The reported performance metrics show the improvement achieved by using our proposed embedding network and fusing both sides of occluded ear images.
PDF
