Chinese Optics Letters, 2008, 6 (11): 824, Published Online: Nov. 17, 2008
Improving iris recognition performance via multi-instance fusion at the score level Download: 527次
生物特征认证 虹膜识别 多实例融合 最小最大概率机 100.5010 Pattern recognition 100.2000 Digital image processing 100.2960 Image analysis
Abstract
Fusion of multiple instances within a modality for biometric verification performance improvement has received considerable attention. In this letter, we present an iris recognition method based on multi-instance fusion, which combines the left and right irises of an individual at the matching score level. When fusing, a novel fusion strategy using minimax probability machine (MPM) is applied to generate a fused score for the final decision. The experimental results on CASIA and UBIRIS databases show that the proposed method can bring obvious performance improvement compared with the single-instance method. The comparison among different fusion strategies demonstrates the superiority of the fusion strategy based on MPM.
Fenghua Wang, Xianghua Yao, Jiuqiang Han. Improving iris recognition performance via multi-instance fusion at the score level[J]. Chinese Optics Letters, 2008, 6(11): 824.