Towards Robust Iris Recognition Through Occlusion Identification and Conditional Diffusion-Based Reconstruction

2026-07-23

AI Summary

This work addresses the performance degradation of iris recognition under occlusions caused by eyelids, eyelashes, or specular reflections, which lead to loss of discriminative texture information. The authors propose an occlusion-aware iris recognition framework that first employs a lightweight residual 2D CNN to classify occlusion types, then leverages a conditional denoising diffusion model for semantically guided image reconstruction, and finally utilizes an enhanced VGG19-HPMNet architecture incorporating horizontal pyramid mapping to strengthen both local and global feature representation. Notably, this approach is the first to jointly optimize occlusion-type identification and conditional diffusion-based reconstruction within a unified pipeline. Experimental results on the CASIA-Iris-Thousand dataset demonstrate significant improvements in recognition accuracy under occluded conditions.

Abstract

Iris recognition is a reliable biometric approach that identifies individuals using the distinctive and stable texture of the iris. However, recognition performance can degrade when discriminative iris texture is partially occluded by eyelids, eyelashes, specular reflections, or other acquisition artifacts. Existing approaches often perform recognition directly on degraded samples or rely only on the remaining visible iris region, which may be inadequate when substantial texture is corrupted. To address this limitation, we propose an occlusion-aware iris recognition framework with three sequential modules: occlusion-type identification, diffusion-based reconstruction, and deep-learning-based recognition. First, a residual 2D CNN-based network determines whether an iris image is non-occluded or belongs to one of the controlled occlusion categories. Second, the occluded image, binary mask, and predicted occlusion type condition a denoising diffusion probabilistic model to reconstruct the corrupted region. Finally, VGG19-HPMNet, a modified VGG19 model with horizontal pyramid mapping, extracts discriminative global and part-wise local iris features for recognition. Experiments on the CASIA-Iris-Thousand dataset under a controlled synthetic-occlusion protocol show that the proposed framework improves iris recognition performance by identifying the occlusion type, reconstructing masked regions, and re-evaluating the restored iris samples.

Problem

• iris recognition
• occlusion
• texture corruption
• biometric degradation
• image reconstruction

Innovation

• occlusion-aware recognition
• conditional diffusion model
• iris reconstruction
• horizontal pyramid mapping
• synthetic occlusion