Deep Representations for Cross-spectral Ocular Biometrics

TL;DR

This paper presents a deep learning approach using CNNs fine-tuned on iris and periocular regions to improve cross-spectral ocular verification, significantly reducing error rates across multiple datasets.

Contribution

It introduces a novel method of fine-tuning CNNs based on face recognition models for cross-spectral iris and periocular matching, with extensive evaluation and fusion strategies.

Findings

Significant reduction in Equal Error Rate compared to state-of-the-art.

Fusion of iris and periocular deep features yields best performance.

Deep representations' depth influences recognition effectiveness.

Abstract

One of the major challenges in ocular biometrics is the cross-spectral scenario, i.e., how to match images acquired in different wavelengths (typically visible (VIS) against near-infrared (NIR)). This article designs and extensively evaluates cross-spectral ocular verification methods, for both the closed and open-world settings, using well known deep learning representations based on the iris and periocular regions. Using as inputs the bounding boxes of non-normalized iris/periocular regions, we fine-tune Convolutional Neural Network(CNN) models (based either on VGG16 or ResNet-50 architectures), originally trained for face recognition. Based on the experiments carried out in two publicly available cross-spectral ocular databases, we report results for intra-spectral and cross-spectral scenarios, with the best performance being observed when fusing ResNet-50 deep representations from both the periocular and iris regions. When compared to the state-of-the-art, we observed that the proposed solution consistently reduces the Equal Error Rate(EER) values by 90% / 93% / 96% and 61% / 77% / 83% on the cross-spectral scenario and in the PolyU Bi-spectral and Cross-eye-cross-spectral datasets. Lastly, we evaluate the effect that the "deepness" factor of feature representations has in recognition effectiveness, and - based on a subjective analysis of the most problematic pairwise comparisons - we point out further directions for this field of research.