Sectored Random Projections for Cancelable Iris Biometrics

Pillai, Jaishanker K.; Patel, Vishal M.; Chellappa, Rama; Ratha, Nalini K.

doi:10.1109/icassp.2010.5495383

Cited by 103 publications

(44 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the random Gaussian matrix in our experiments, though other random matrices mentioned in Section VII-A also gave similar results. In [39], it was shown that separate application of the random projections performed better when compared to the application of a single random projection on the entire iris vector. So we vectorized the real part of the Gabor features of each sector of the iris image, applied the random projections, and then concatenated the random projected vectors to obtain our cancelable iris biometric.…”

Section: Cancelability Results Using Random Projectionsmentioning

confidence: 99%

“…The idea of using Random Projections (RP) for cancelability in biometrics has been previously introduced in [28], [38], [39]. In [28] and [38], RPs of discriminative features were used for cancelability in face biometrics.…”

Section: A Cancelability Through Random Projectionsmentioning

confidence: 99%

“…In [28] and [38], RPs of discriminative features were used for cancelability in face biometrics. RPs on different regions of the iris were applied for cancelability in [39]. In what follows, we show how RPs can be extended into the sparse representation-based approach for ensuring cancelability.…”

Section: A Cancelability Through Random Projectionsmentioning

confidence: 99%

See 2 more Smart Citations

Secure and Robust Iris Recognition Using Random Projections and Sparse Representations

Pillai

Patel

Chellappa

et al. 2011

IEEE Trans. Pattern Anal. Mach. Intell.

296

163

View full text Add to dashboard Cite

Abstract-Non-contact biometrics such as face and iris have additional benefits over contact based biometrics such as fingerprint and hand geometry. However, three important challenges need to be addressed in a non-contact biometrics-based authentication system: ability to handle unconstrained acquisition, robust and accurate matching and privacy enhancement without compromising security. In this paper, we propose a unified framework based on random projections and sparse representations, that can simultaneously address all the three issues mentioned above in relation to iris biometrics. Our proposed quality measure can handle segmentation errors and a wide variety of possible artifacts during iris acquisition. We demonstrate how the proposed approach can be easily extended to handle alignment variations and recognition from iris videos, resulting in a robust and accurate system. The proposed approach includes enhancements to privacy and security by providing ways to create cancelable iris templates. Results on public datasets show significant benefits of the proposed approach.

show abstract

Section: Cancelability Results Using Random Projectionsmentioning

confidence: 99%

Section: A Cancelability Through Random Projectionsmentioning

confidence: 99%

See 1 more Smart Citation

Secure and Robust Iris Recognition Using Random Projections and Sparse Representations

Pillai

Patel

Chellappa

et al. 2011

IEEE Trans. Pattern Anal. Mach. Intell.

296

163

View full text Add to dashboard Cite

show abstract

“…Different dimensionality reduction methods are used to reduce the dimension of both the test vector and the vectors in the dictionary. One such approach for dimensionality reduction is random projections [19]. Random projections, using a generated sensing matrix, are taken of both the dictionary matrix and the test sample.…”

Section: Sparse Representation-based Classificationmentioning

confidence: 99%

Dictionaries for image-based recognition

Patel

Qiu

Chellappa

2013

2013 Information Theory and Applications Workshop (ITA)

View full text Add to dashboard Cite

Abstract-In recent years, Sparse Representation (SR) and Dictionary Learning (DL) have emerged as powerful tools for efficiently processing of image and video data in non-traditional ways. An area of promise for these theories is object recognition. In this paper, we present an overview of SR and DR and examine several interesting object recognition approaches using these theories. We will also explore the use of non-linear kernel SR as well as DL methods in many computer vision problems including object recognition, multimodal biometrics recognition, and domain adaptation.

show abstract

“…This is a non-invertible transformation that discards information, and as such, sacrifices performance. [13] is one such example that randomly projects segments of the iris data. More recently, [14] improves on earlier work, reporting TAR=98.13 at FAR=0.001 on the ICE2005 dataset.…”

Section: State-of-the-art Private Iris Verificationmentioning

confidence: 99%

PRIVV: Private remote iris-authentication with Vaulted Verification

Wilber

Scheirer

Boult

2012

2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

Iris biometrics are one of the strongest modalities in terms of performance, and as such, are used in several highsecurity scenarios. However, remote/network authentication creates its own class of problems that have not previously been considered. In this work, we adapt Vaulted Verification, a novel remote matching protocol, to work with iris biometrics in a network authentication setting. We give an overview of how Vaulted Verification works and show how to adapt it to the unique challenges of iris biometrics. We then investigate the algorithm's security and evaluate its performance, showing that Vaulted Verification is among the top-performing template protection algorithms for the CASIAv1 dataset. We conclude with a summary and ideas for future work.

show abstract

Sectored Random Projections for Cancelable Iris Biometrics

Cited by 103 publications

References 11 publications

Secure and Robust Iris Recognition Using Random Projections and Sparse Representations

Secure and Robust Iris Recognition Using Random Projections and Sparse Representations

Dictionaries for image-based recognition

PRIVV: Private remote iris-authentication with Vaulted Verification

Contact Info

Product

Resources

About