# IRIS-QResNet: A Quantum-Inspired Deep Model for Efficient Iris Biometric Identification and Authentication

## TL;DR

IRIS-QResNet is a new deep learning model that improves iris recognition accuracy using quantum-inspired techniques, especially when training data is limited.

## Contribution

Introduces a quantum-inspired quanvolutional layer to enhance feature extraction in ResNet for iris recognition without data augmentation.

## Key findings

- IRIS-QResNet outperforms IResNet with up to 16.67% higher identification accuracy on benchmark datasets.
- The model achieves lower loss values and consistent performance across four iris datasets without data augmentation.
- Quantum-inspired modifications improve discriminative power and data efficiency in residual networks.

## Abstract

IRIS-QResNet, a custom ResNet model enhanced with a quanvolutional layer for more accurate iris recognition that uses few samples per subject without applying augmentation.IRIS-QResNet proves its ability for efficient biometric authentication by consistently achieving superior accuracy and generalization across four benchmark datasets.

IRIS-QResNet, a custom ResNet model enhanced with a quanvolutional layer for more accurate iris recognition that uses few samples per subject without applying augmentation.

IRIS-QResNet proves its ability for efficient biometric authentication by consistently achieving superior accuracy and generalization across four benchmark datasets.

What are the main findings?
Compared with IResNet, the traditional baseline, IRIS-QResNet model significantly improves recognition accuracy and robustness, even in small-sample, augmentation-free settings.Across multiple iris datasets, IRIS-QResNet strengthens multilayer feature extraction, resulting in measurable performance gains of up to 16.66% in identification accuracy.

Compared with IResNet, the traditional baseline, IRIS-QResNet model significantly improves recognition accuracy and robustness, even in small-sample, augmentation-free settings.

Across multiple iris datasets, IRIS-QResNet strengthens multilayer feature extraction, resulting in measurable performance gains of up to 16.66% in identification accuracy.

What are the implications of the main findings?
By effectively integrating quantum-inspired layers into classical deep networks, higher discriminative power and data efficiency can be achieved, reducing dependence on large training datasets and data augmentation.These results open the path toward scalable and sustainable AI solutions for biometric systems, establishing a viable bridge between conventional and emerging quantum machine learning architectures.

By effectively integrating quantum-inspired layers into classical deep networks, higher discriminative power and data efficiency can be achieved, reducing dependence on large training datasets and data augmentation.

These results open the path toward scalable and sustainable AI solutions for biometric systems, establishing a viable bridge between conventional and emerging quantum machine learning architectures.

Iris recognition continues to pose challenges for deep learning models, despite its status as one of the most reliable biometric authentication techniques. These challenges become more pronounced when training data is limited, as subtle, high-dimensional patterns are easily missed. To address this issue and strengthen both feature extraction and recognition accuracy, this study introduces IRIS-QResNet, a customized ResNet-18 architecture augmented with a quanvolutional layer. The quanvolutional layer simulates quantum effects such as entanglement and superposition and incorporates sinusoidal feature encoding, enabling more discriminative multilayer representations. To evaluate the model, we conducted 14 experiments on the CASIA-Thousands, IITD, MMU, and UBIris datasets, comparing the performance of the proposed IRIS-QResNet with that of the IResNet baseline. While IResNet occasionally yielded subpar accuracy, ranging from 50.00% to 98.66%, and higher loss values ranging from 0.1060 to 2.0640, comparative analyses showed that IRIS-QResNet consistently outperformed it. IRIS-QResNet achieved lower loss (ranging from 0.0570 to 1.8130), higher accuracy (ranging from 66.67% to 99.55%), and demon-started improvement margins spanning from 0.1870% in the CASIA End-to-End subject recognition with eye-side to 16.67% in the MMU End-to-End subject recognition with eye-side. Loss reductions ranged from 0.0360 in the CASIA End-to-End subject recognition without eye-side to 1.0280 in the UBIris Non-End-to-End subject recognition. Overall, the model exhibited robust generalization across recognition tasks despite the absence of data augmentation. These findings indicate that quantum-inspired modifications provide a practical and scalable approach for enhancing the discriminative capacity of residual networks, offering a promising bridge between classical deep learning and emerging quantum machine learning paradigms.