The Impact of Preprocessing on Deep Representations for Iris Recognition on Unconstrained Environments

TL;DR

This paper explores the use of deep learning architectures like VGG and ResNet-50, combined with transfer learning and data augmentation, to improve iris recognition accuracy in unconstrained environments without relying on traditional preprocessing techniques.

Contribution

It introduces a novel approach using deep representations with minimal preprocessing, achieving state-of-the-art results on challenging iris datasets.

Findings

Achieved a new state-of-the-art EER of 13.98% on NICE.II dataset.

Deep features outperform traditional preprocessing methods.

Transfer learning from face recognition enhances iris recognition performance.

Abstract

The use of iris as a biometric trait is widely used because of its high level of distinction and uniqueness. Nowadays, one of the major research challenges relies on the recognition of iris images obtained in visible spectrum under unconstrained environments. In this scenario, the acquired iris are affected by capture distance, rotation, blur, motion blur, low contrast and specular reflection, creating noises that disturb the iris recognition systems. Besides delineating the iris region, usually preprocessing techniques such as normalization and segmentation of noisy iris images are employed to minimize these problems. But these techniques inevitably run into some errors. In this context, we propose the use of deep representations, more specifically, architectures based on VGG and ResNet-50 networks, for dealing with the images using (and not) iris segmentation and normalization. We use transfer learning from the face domain and also propose a specific data augmentation technique for iris images. Our results show that the approach using non-normalized and only circle-delimited iris images reaches a new state of the art in the official protocol of the NICE.II competition, a subset of the UBIRIS database, one of the most challenging databases on unconstrained environments, reporting an average Equal Error Rate (EER) of 13.98% which represents an absolute reduction of about 5%.