Topological Invariant-Based Iris Identification via Digital Homology and Machine Learning

2025-08-13

AI Summary

To address model redundancy, poor interpretability, and high computational demands of deep learning methods in iris recognition, this paper introduces formal digital homology theory—novel in biometric recognition—and proposes a lightweight iris representation method based on topological invariants (Betti numbers). Standardized iris images are partitioned into grids to extract robust topological features, which are subsequently reduced via PCA and classified using conventional classifiers such as logistic regression. Experiments demonstrate that logistic regression achieves 97.78±0.82% accuracy—significantly outperforming CNNs under identical configuration—while exhibiting lower variance and enabling efficient inference on CPU-only hardware. The approach delivers high accuracy, strong interpretability, minimal computational overhead, and effective small-sample adaptation. It establishes a new paradigm for resource-constrained or high-security authentication scenarios.

Technology Category

• Computer Vision: Representation Learning for Vision
• Machine Learning: Representation Learning
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Security and Privacy: Large-scale security measurements
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Objective - This study presents a biometric identification method based on topological invariants from 2D iris images, representing iris texture via formally defined digital homology and evaluating classification performance. Methods - Each normalized iris image (48x482 pixels) is divided into grids (e.g., 6x54 or 3x27). For each subregion, we compute Betti0, Betti1, and their ratio using a recent algorithm for homology groups in 2D digital images. The resulting invariants form a feature matrix used with logistic regression, KNN, and SVM (with PCA and 100 randomized repetitions). A convolutional neural network (CNN) is trained on raw images for comparison. Results - Logistic regression achieved 97.78 +/- 0.82% accuracy, outperforming CNN (96.44 +/- 1.32%) and other feature-based models. The topological features showed high accuracy with low variance. Conclusion - This is the first use of topological invariants from formal digital homology for iris recognition. The method offers a compact, interpretable, and accurate alternative to deep learning, useful when explainability or limited data is important. Beyond iris recognition, it can apply to other biometrics, medical imaging, materials science, remote sensing, and interpretable AI. It runs efficiently on CPU-only systems and produces robust, explainable features valuable for security-critical domains.

Problem

• Develops iris identification using topological invariants and machine learning
• Compares performance of logistic regression, KNN, SVM, and CNN
• Provides interpretable alternative to deep learning for biometrics

Innovation

• Uses digital homology for iris texture analysis
• Combines Betti numbers with machine learning
• Provides explainable alternative to deep learning