CLRecogEye : Curriculum Learning towards exploiting convolution features for Dynamic Iris Recognition

2025-11-26

AI Summary

Existing iris recognition methods suffer from insufficient robustness against rotational variance, scale changes, specular reflections, and defocus blur, while neglecting spatiotemporal structural modeling. To address this, we propose an end-to-end matching framework based on sequential patching and 3D convolutional neural networks (3D-CNNs). Our approach innovatively introduces curriculum learning into iris recognition: normalized iris images are partitioned along the angular dimension and reformulated as temporal sequences, enabling 3D-CNNs to capture local texture dynamics in both spatial and temporal domains. Furthermore, temporal dependencies are explicitly embedded within the deep metric space, and triplet loss is jointly optimized with ArcFace loss. Experiments demonstrate that our method significantly improves recognition accuracy, generalization capability, and deployment stability under diverse challenging conditions, including severe geometric distortions and optical degradations.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements

Abstract

Iris authentication algorithms have achieved impressive recognition performance, making them highly promising for real-world applications such as border control, citizen identification, and both criminal investigations and commercial systems. However, their robustness is still challenged by variations in rotation, scale, specular reflections, and defocus blur. In addition, most existing approaches rely on straightforward point-to-point comparisons, typically using cosine or L2 distance, without effectively leveraging the spatio-spatial-temporal structure of iris patterns. To address these limitations, we propose a novel and generalized matching pipeline that learns rich spatio-spatial-temporal representations of iris features. Our approach first splits each iris image along one dimension, generating a sequence of sub-images that serve as input to a 3D-CNN, enabling the network to capture both spatial and spatio-spatial-temporal cues. To further enhance the modeling of spatio-spatial-temporal feature dynamics, we train the model in curriculum manner. This design allows the network to embed temporal dependencies directly into the feature space, improving discriminability in the deep metric domain. The framework is trained end-to-end with triplet and ArcFace loss in a curriculum manner, enforcing highly discriminative embeddings despite challenges like rotation, scale, reflections, and blur. This design yields a robust and generalizable solution for iris authentication.Github code: https://github.com/GeetanjaliGTZ/CLRecogEye

Problem

• Dynamic iris recognition challenged by rotation, scale, reflections, and blur
• Existing methods lack spatio-temporal structure exploitation in iris patterns
• Need for robust feature embeddings that capture temporal iris dependencies

Innovation

• Uses 3D-CNN for spatio-temporal iris features
• Splits iris images into sequential sub-images
• Employs curriculum learning with triplet loss