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.

© 2008 Chinese Optics Letters

Optimal wavelength band clustering for multispectral iris recognition

Yazhuo Gong, David Zhang, Pengfei Shi, and Jingqi Yan
Appl. Opt. 51(19) 4275-4284 (2012)

Double random phase encoding for cancelable face and iris recognition

Randa F. Soliman, Ghada M. El Banby, Abeer D. Algarni, Mohamed Elsheikh, Naglaa F. Soliman, Mohamed Amin, and Fathi E. Abd El-Samie
Appl. Opt. 57(35) 10305-10316 (2018)

Extending the imaging volume for biometric iris recognition

Ramkumar Narayanswamy, Gregory E. Johnson, Paulo E. X. Silveira, and Hans B. Wach
Appl. Opt. 44(5) 701-712 (2005)

Target detection and recognition improvements by use of spatiotemporal fusion

Hai-Wen Chen, Surachai Sutha, and Teresa Olson
Appl. Opt. 43(2) 403-415 (2004)

Point spread function engineering for iris recognition system design

Amit Ashok and Mark A. Neifeld
Appl. Opt. 49(10) B26-B39 (2010)