Hierarchical fusion network for periocular and iris by neural network approximation and sparse autoencoder
- PDF / 1,114,393 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 86 Downloads / 203 Views
ORIGINAL PAPER
Hierarchical fusion network for periocular and iris by neural network approximation and sparse autoencoder Faisal Algashaam1 · Kien Nguyen1
· Jasmine Banks1 · Vinod Chandran1 · Tuan-Anh Do3 · Mohamed Alkanhal2
Received: 2 June 2019 / Revised: 17 May 2020 / Accepted: 12 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract The eye region is one of the most attractive sources for identification and verification due to the representative availability of such biometric modalities as periocular and iris. Many score-level fusion approaches have been proposed to combine these two modalities targeting to improve the robustness. The score-level approaches can be grouped into three categories: transformation-based, classification-based and density-based. Each category has its own benefits, if combined can lead to a robust fusion mechanism. In this paper, we propose a hierarchical fusion network to fuse multiple fusion approaches from transformation-based and classification-based categories into a unified framework for classification. The proposed hierarchical approach relies on the universal approximation theorem for neural networks to approximate each fusion approach as one child neural network and then ensemble them into a unified parent network. This mechanism takes advantage of both categories to improve the fusion performance, illustrated by an improved equal error rate of the multimodal biometric system. We subsequently force the parent network to learn the representation and interaction strategy between the child networks from the training data through a sparse autoencoder layer, leading to further improvements. Experiments on two public datasets (MBGC version 2 and CASIA-Iris-Thousand) and our own dataset validate the effectiveness of the proposed hierarchical fusion approach for periocular and iris modalities. Keywords Periocular recognition · Iris recognition · Hierarchical multimodal fusion · Neural network approximation · Sparse autoencoder
1 Introduction
B
Kien Nguyen [email protected] Faisal Algashaam [email protected] Jasmine Banks [email protected] Vinod Chandran [email protected] Tuan-Anh Do [email protected] Mohamed Alkanhal [email protected]
1
Queensland University of Technology, Brisbane, QLD, Australia
2
King Abdulaziz City for Science and Technology, Riyadh, Saudi Arabia
3
Hanoi University of Science and Technology, Hanoi, Vietnam
Biometrics, the knowledge of determining the identity of a person through the use of physical and/or behavioural traits, have gaining significant attention considering the increasing incidents of fraud challenges in highly secure identity authentication systems. Unlike traditional knowledge-based (e.g. PINs, passwords) and token-based (e.g. cards, keys) approaches, biometrics rely on human’s intrinsic characteristics which cannot be easily lost, forgotten or shared. Several human physiological (e.g. fingerprint, face, iris, palm vein, retina and ear) and behavioural (e.g. keystrok
Data Loading...
