Comparison of Recognition Fusion Methods for Left and Right Off-Angle Iris Images

Robust iris recognition performance remains a significant challenge, especially for off-angle images captured in less constrained environments. While convolutional neural networks (CNNs) have shown great promise in iris recognition, there is limited research on the effects of gaze-angle distortions on recognition performance and the development of dedicated frameworks for off angle iris recognition. This study investigates different recognition fusion strategies for left and right off-angle iris images using deep learning. A transfer learning approach leveraging the pre-trained AlexNet model is employed to classify iris images, where frontal-view iris images are used for training and off-angle images for testing. Three fusion strategies are explored: (i) a double model approach with decision-level fusion, where separate models are trained for left and right irises and their predictions are combined, (ii) a single model approach with feature-level fusion, where a unified model extracts and fuses features from both irises, and (iii) a single model approach with image-level fusion, where left and right iris images are merged at the input level. The performance of these methods is evaluated using accuracy as the primary metric to assess the model's generalization capabilities under off-angle conditions. Experimental results highlight the advantages and trade-offs of each fusion strategy, offering insights into the role of bilateral iris information in enhancing recognition performance. The findings of this study contribute to the development of more robust deep learning-based iris recognition systems capable of handling off-angle variations.