Texture Aware Autoencoder Pre-training And Pairwise Learning Refinement For Improved Iris Recognition

TL;DR

This paper introduces a texture-aware autoencoder pre-training and pairwise learning refinement for iris recognition, significantly improving accuracy on limited datasets by enhancing texture representation and integrating matching into the training process.

Contribution

It proposes a novel end-to-end iris recognition system with texture-aware pretraining and pairwise learning, advancing beyond traditional methods for limited data scenarios.

Findings

Outperforms traditional and deep learning baselines

Effective on multiple iris datasets

Improves recognition accuracy in constrained data settings

Abstract

This paper presents a texture aware end-to-end trainable iris recognition system, specifically designed for datasets like iris having limited training data. We build upon our previous stagewise learning framework with certain key optimization and architectural innovations. First, we pretrain a Stage-1 encoder network with an unsupervised autoencoder learning optimized with an additional data relation loss on top of usual reconstruction loss. The data relation loss enables learning better texture representation which is pivotal for a texture rich dataset such as iris. Robustness of Stage-1 feature representation is further enhanced with an auxiliary denoising task. Such pre-training proves beneficial for effectively training deep networks on data constrained iris datasets. Next, in Stage-2 supervised refinement, we design a pairwise learning architecture for an end-to-end trainable iris recognition system. The pairwise learning includes the task of iris matching inside the training pipeline itself and results in significant improvement in recognition performance compared to usual offline matching. We validate our model across three publicly available iris datasets and the proposed model consistently outperforms both traditional and deep learning baselines for both Within-Dataset and Cross-Dataset configurations