DeepIris: Learning pairwise filter bank for heterogeneous iris verification

Abstract

Heterogeneous iris recognition (HIR) is in great demand for a large-scale identity management system. Iris images acquired in heterogeneous environment have large intra-class variations, such as different resolutions or different sensor optics, etc. Therefore, it is challenging to manually design a robust encoding filter to face the complex intra-class variations of heterogeneous iris images. This paper proposes a deep learning based framework for heterogeneous iris verification, namely DeepIris, which learns relational features to measure the similarity between pairs of iris images based on convolutional neural networks. DeepIris is a novel solution to iris recognition in two main aspects. (1) DeepIris learns a pairwise filter bank to establish the relationship between heterogeneous iris images, where pairs of filters are learned from two heterogeneous sources. (2) Different from two separate steps in terms of handcrafted feature extraction and feature matching in conventional solutions, DeepIris directly learns a nonlinear mapping function between pairs of iris images and their identity supervision with a pairwise filter bank (PFB) from different sources. Thus, the learned pairwise filters can adapt to new sources when given new training data. Extensive experimental results on the Q-FIRE and the CASIA cross sensor datasets demonstrate that EER (Equal Error Rate) of heterogeneous iris verification is reduced by 90% using DeepIris compared to traditional methods.