Experimental study on the impact of robust watermarking on iris recognition accuracy

Hämmerle-Uhl, Jutta; Raab, Karl; Uhl, Andreas

doi:10.1145/1774088.1774405

Cited by 28 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since in any biometric application scenario there is no unmarked original image available to detect the WM in the marked image, only blind WM techniques are applicable in this context. We consider a variety of robust watermarking techniques in different flavours which have been also used to assess the impact of robust WM on iris recognition performance [4].…”

Section: Setting and Methodsmentioning

confidence: 99%

“…While this specific attack is targeted against the security of robust embedding (and can be eventually resolved by using different types of watermarks), robust watermarking additionally introduces distortions into the sample data impacting on recognition performance [4]. A concatenation of data (sample data and "embedded" template data) plus additional cryptographic authentication seems to be an alternative without this undesired effect.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Attack against Robust Watermarking-Based Multimodal Biometric Recognition Systems

Hämmerle-Uhl

Raab

Uhl

2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Several multimodal biometric schemes have been suggested in literature which employ robust watermarking in order to embed biometric template data into biometric sample data. In case robust embedding is used as the sole means of security, tampering attacks can be mounted. The results of a corresponding attack against a multimodal iris recognition scheme show, that in this environment either semi-fragile watermarking or additional classical cryptographic means need to be applied to secure the system against the demonstrated attack.

show abstract

Section: Setting and Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Attack against Robust Watermarking-Based Multimodal Biometric Recognition Systems

Hämmerle-Uhl

Raab

Uhl

2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hammerle-Uhl et al [17] provide an experimental study of how different watermarking methods influence iris recognition. The authors claim that regular watermarking, that presents some robustness against image alterations, degrades biometric accuracy.…”

Section: Past Workmentioning

confidence: 99%

Verification of iris image authenticity using fragile watermarking

Czajka

Kasprzak

Wilkowski

2016

Bulletin of the Polish Academy of Sciences Technical Sciences

View full text Add to dashboard Cite

Abstract. This paper proposes and evaluates a watermarking-based approach to certify the authenticity of iris images when they are captured by a genuine equipment. In the proposed method, the iris images are secretly signed before being used in biometric processes, and the resulting signature is embedded into the JPEG carrier image in the DCT domain in a data-dependent way. Any alteration of the original (certified) image makes the signature no longer corresponding to this image and this change can be quickly identified at the receiver site. Hence, it is called fragile watermarking to differentiate this method from regular watermarking that should present some robustness against image alterations. There is no need to attach any auxiliary signature data, hence the existing, already standardized transmission channels and storage protocols may be used. The embedding procedure requires to remove some part of the original information. But, by using the BATH dataset comprising 32 000 iris images collected for 1 600 distinct eyes, we verify that the proposed alterations have no impact on iris recognition reliability, although statistically significant, small differences in genuine score distributions are observed when the watermark is embedded to both the enrollment and verification iris images. This is a unique evaluation of how the watermark embedding of digital signatures into the ISO CROPPED iris images (during the enrollment, verification or both) influences the reliability of a well-established, commercial iris recognition methodology. Without loss in generality, this approach is targeted to biometric-enabled ID documents that deploy iris data to authenticate the holder of the document.

show abstract

“…While Dong et al [2] do not report on performance degradations when investigating a single watermark embedding algorithm and one iris recognition technique only, Hämmerle et al [3] find partially significant reductions in recognition accuracy (especially in case of high capacity) when assessing two iris recognition schemes and a couple of robust watermarking algorithms. Similar to the latter results, recognition impact has been observed as well for speech recognition [10] and fingerprint recognition [14].…”

Section: Watermarking In Biometric Systemsmentioning

confidence: 99%

“…While this specific attack discussed is targeted against the security of robust embedding (and can be resolved by using different types of watermarks as shown in this work), robust watermarking additionally introduces distortions into the sample data impacting on recognition performance [3]. Also for this problem, different types of watermarks may represent better solutions as also covered here.…”

Section: Introductionmentioning

confidence: 99%

Two-Factor Biometric Recognition with Integrated Tamper-Protection Watermarking

Huber

Stögner

Uhl

2011

Communications and Multimedia Security

Self Cite

View full text Add to dashboard Cite

Abstract. Two-factor authentication with biometrics and smart-cards enabled by semi-fragile watermarking is proposed. Several advantages of the scheme as compared to earlier approaches are discussed and experiments for an iris-based recognition system demonstrate that semi-fragile integrity verification can be provided by the system. This is achieved without impact on recognition performance, since the slight degradation in terms of ROC behavior which is observed on the watermarked sample data is more than compensated by the additionally available template that is transferred from the smart-card to the matching site via watermarking technology.

show abstract

Experimental study on the impact of robust watermarking on iris recognition accuracy

Cited by 28 publications

References 18 publications

Attack against Robust Watermarking-Based Multimodal Biometric Recognition Systems

Attack against Robust Watermarking-Based Multimodal Biometric Recognition Systems

Verification of iris image authenticity using fragile watermarking

Two-Factor Biometric Recognition with Integrated Tamper-Protection Watermarking

Contact Info

Product

Resources

About