Adaptive Deep Iris Feature Extractor at Arbitrary Resolutions

TL;DR

This paper introduces a resolution-adaptive deep iris feature extractor that automatically switches between specialized modules to improve recognition accuracy across various image resolutions, addressing the limitations of fixed-resolution models.

Contribution

The proposed framework employs resolution expert modules with automatic switching and knowledge distillation, enhancing iris recognition performance at multiple resolutions.

Findings

Improved recognition accuracy at low resolutions.

Maintained high-resolution recognition performance.

Effective across multiple neural network architectures.

Abstract

This paper proposes a deep feature extractor for iris recognition at arbitrary resolutions. Resolution degradation reduces the recognition performance of deep learning models trained by high-resolution images. Using various-resolution images for training can improve the model's robustness while sacrificing recognition performance for high-resolution images. To achieve higher recognition performance at various resolutions, we propose a method of resolution-adaptive feature extraction with automatically switching networks. Our framework includes resolution expert modules specialized for different resolution degradations, including down-sampling and out-of-focus blurring. The framework automatically switches them depending on the degradation condition of an input image. Lower-resolution experts are trained by knowledge-distillation from the high-resolution expert in such a manner that both experts can extract common identity features. We applied our framework to three conventional neural network models. The experimental results show that our method enhances the recognition performance at low-resolution in the conventional methods and also maintains their performance at high-resolution.