Iris authentication using privatized advanced correlation filter

his paper proposes a private biometrics formulation which is based on the concealment of random kernel and the iris images to synthesize a minimum average correlation energy (MACE) filter for iris authentication. Specifically, we multiply training images with the user-specific random kernel in frequ...

Full description

Bibliographic Details
Main Authors: Chong, , SC, Teoh, , ABJ, Ngo, , DCL
Format: Article
Published: 2006
Subjects:
Online Access:http://shdl.mmu.edu.my/2025/
_version_ 1848789943048994816
author Chong, , SC
Teoh, , ABJ
Ngo, , DCL
author_facet Chong, , SC
Teoh, , ABJ
Ngo, , DCL
author_sort Chong, , SC
building MMU Institutional Repository
collection Online Access
description his paper proposes a private biometrics formulation which is based on the concealment of random kernel and the iris images to synthesize a minimum average correlation energy (MACE) filter for iris authentication. Specifically, we multiply training images with the user-specific random kernel in frequency domain before biometric filter is created. The objective of the proposed method is to provide private biometrics realization in iris authentication in which biometric template can be reissued once it was compromised. Meanwhile, the proposed method is able to decrease the computational load, due to the filter size reduction. It also improves the authentication rate significantly compare to the advance correlation based approach [5][6] and comparable to the Daugmant's Iris Code [1].
first_indexed 2025-11-14T18:04:45Z
format Article
id mmu-2025
institution Multimedia University
institution_category Local University
last_indexed 2025-11-14T18:04:45Z
publishDate 2006
recordtype eprints
repository_type Digital Repository
spelling mmu-20252011-08-10T07:01:24Z http://shdl.mmu.edu.my/2025/ Iris authentication using privatized advanced correlation filter Chong, , SC Teoh, , ABJ Ngo, , DCL QA75.5-76.95 Electronic computers. Computer science his paper proposes a private biometrics formulation which is based on the concealment of random kernel and the iris images to synthesize a minimum average correlation energy (MACE) filter for iris authentication. Specifically, we multiply training images with the user-specific random kernel in frequency domain before biometric filter is created. The objective of the proposed method is to provide private biometrics realization in iris authentication in which biometric template can be reissued once it was compromised. Meanwhile, the proposed method is able to decrease the computational load, due to the filter size reduction. It also improves the authentication rate significantly compare to the advance correlation based approach [5][6] and comparable to the Daugmant's Iris Code [1]. 2006 Article NonPeerReviewed Chong, , SC and Teoh, , ABJ and Ngo, , DCL (2006) Iris authentication using privatized advanced correlation filter. ADVANCES IN BIOMETRICS, PROCEEDINGS, 3832. pp. 382-388. ISSN 0302-9743
spellingShingle QA75.5-76.95 Electronic computers. Computer science
Chong, , SC
Teoh, , ABJ
Ngo, , DCL
Iris authentication using privatized advanced correlation filter
title Iris authentication using privatized advanced correlation filter
title_full Iris authentication using privatized advanced correlation filter
title_fullStr Iris authentication using privatized advanced correlation filter
title_full_unstemmed Iris authentication using privatized advanced correlation filter
title_short Iris authentication using privatized advanced correlation filter
title_sort iris authentication using privatized advanced correlation filter
topic QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2025/