ThirdEye: Triplet Based Iris Recognition without Normalization

TL;DR

ThirdEye introduces a triplet CNN-based iris recognition system that bypasses normalization, achieving competitive accuracy on constrained datasets and questioning the necessity of normalization in less controlled environments.

Contribution

The paper presents a novel iris recognition approach using triplet CNNs that eliminates the normalization step, challenging traditional pipelines.

Findings

Achieves 1.32% EER on ND-0405 dataset

Achieves 9.20% EER on UbirisV2 dataset

Achieves 0.59% EER on IITD dataset

Abstract

Most iris recognition pipelines involve three stages: segmenting into iris/non-iris pixels, normalization the iris region to a fixed area, and extracting relevant features for comparison. Given recent advances in deep learning it is prudent to ask which stages are required for accurate iris recognition. Lojez et al. (IWBF 2019) recently concluded that the segmentation stage is still crucial for good accuracy.We ask if normalization is beneficial? Towards answering this question, we develop a new iris recognition system called ThirdEye based on triplet convolutional neural networks (Schroff et al., ICCV 2015). ThirdEye directly uses segmented images without normalization. We observe equal error rates of 1.32%, 9.20%, and 0.59% on the ND-0405, UbirisV2, and IITD datasets respectively. For IITD, the most constrained dataset, this improves on the best prior work. However, for ND-0405 and UbirisV2,our equal error rate is slightly worse than prior systems. Our concluding hypothesis is that normalization is more important for less constrained environments.