Cross-sensor periocular biometrics in a global pandemic: Comparative benchmark and novel multialgorithmic approach

ABSTRACT

The massive availability of cameras and personal devices results in a wide variability between imaging conditions, producing large intra-class variations and a significant performance drop if images from heterogeneous environments are compared for person recognition purposes. However, as biometric solutions are extensively deployed, it will be common to replace acquisition hardware as it is damaged or newer designs appear or to exchange information between agencies or applications operating in different environments. Furthermore, variations in imaging spectral bands can also occur. For example, face images are typically acquired in the visible (VIS) spectrum, while iris images are usually captured in the near-infrared (NIR) spectrum. However, cross-spectrum comparison may be needed if, for example, a face image obtained from a surveillance camera needs to be compared against a legacy database of iris imagery. Here, we propose a multialgorithmic approach to cope with periocular images captured with different sensors. With face masks in the front line to fight against the COVID-19 pandemic, periocular recognition is regaining popularity since it is the only region of the face that remains visible. As a solution to the mentioned cross-sensor issues, we integrate different biometric comparators using a score fusion scheme based on linear logistic regression This approach is trained to improve the discriminating ability and, at the same time, to encourage that fused scores are represented by log-likelihood ratios. This allows easy interpretation of output scores and the use of Bayes thresholds for optimal decision-making since scores from different comparators are in the same probabilistic range. We evaluate our approach in the context of the 1st Cross-Spectral Iris/Periocular Competition, whose aim was to compare person recognition approaches when periocular data from visible and near-infrared images is matched. The proposed fusion approach achieves reductions in the error rates of up to 30%–40% in cross-spectral NIR-VIS comparisons with respect to the best individual system, leading to an EER of 0.2% and a FRR of just 0.47% at FAR = 0.01%. It also represents the best overall approach of the mentioned competition. Experiments are also reported with a database of VIS images from two different smartphones as well, achieving even bigger relative improvements and similar performance numbers. We also discuss the proposed approach from the point of view of template size and computation times, with the most computationally heavy comparator playing an important role in the results. Lastly, the proposed method is shown to outperform other popular fusion approaches in multibiometrics, such as the average of scores, Support Vector Machines, or Random Forest.