Hybrid Fusion Framework for Iris Recognition Systems

摘要: Due to the advantages in uniqueness, convenience and non-contact, iris recognition is widely deployed for automatic identity authentication. Instead of a single signature, multiple templates are registered real-world applications diversity gallery samples, resulting great enhanced user experience. In this paper, we exploit connection among registration data then make efforts give more comprehensive decision based on them. A novel hybrid fusion framework proposed fuse information at groups feature score levels. Specifically, samples firstly divided into balance abundance robustness information. Afterwards, hierarchical performed groups, which actually procedure mapping reducing. The experimental results demonstrate effectiveness generalization ability framework.