On the Impact of Different Fabrication Materials on Fingerprint Presentation Attack Detection

Gonzalez-Soler, Lazaro J.; Gomez‐Barrero, Marta; Chang, Leonardo; Suárez, Airel Pérez; Busch, Christoph

doi:10.1109/icb45273.2019.8987425

Cited by 13 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that for the unknown PAI species protocol described in [10], the FV method shows an ACER below 1.00% for most datasets, with the exception of Biometrika 2011 and Italdata 2011, which contain unknown PAIs fabricated with Silgum. In a previous work [47], we showed how PAIs created with Silgum correctly copied their corresponding fingerprint ridge pattern, thereby making hard to detect by our best fingerprint representation. On the other hand, the ACERs showed by FV and the fusion method for LivDet 2015 also appear to be affected by the aforementioned fingerprint quality.…”

Section: ) Known Capture Device and Unknown-materials Scenariomentioning

confidence: 96%

Fingerprint Presentation Attack Detection Based on Local Features Encoding for Unknown Attacks

et al. 2021

Self Cite

View full text Add to dashboard Cite

Fingerprint-based biometric systems have experienced a large development in the past. In spite of many advantages, they are still vulnerable to attack presentations (APs). Therefore, the task of determining whether a sample stems from a live subject (i.e., bona fide) or from an artificial replica is a mandatory requirement which has recently received a considerable attention. Nowadays, when the materials for the fabrication of the Presentation Attack Instruments (PAIs) have been used to train the Presentation Attack Detection (PAD) methods, the PAIs can be successfully identified in most cases. However, current PAD methods still face difficulties detecting PAIs built from unknown materials and/or unknown recepies, or acquired using different capture devices. To tackle this issue, we propose a new PAD technique based on three image representation approaches combining local and global information of the fingerprint. By transforming these representations into a common feature space, we can correctly discriminate bona fide from attack presentations in the aforementioned scenarios. The experimental evaluation of our proposal over the LivDet 2011 to 2019 databases, yielded error rates outperforming the top state-of-the-art results by up to 72% in the most challenging scenarios. In addition, the best representation achieved the best results in the LivDet 2019 competition (overall accuracy of 96.17%).INDEX TERMS Local feature encoding, presentation attack detection, fingerprint, probabilistic visual vocabulary, visual vocabulary.

show abstract

Section: ) Known Capture Device and Unknown-materials Scenariomentioning

confidence: 96%

Fingerprint Presentation Attack Detection Based on Local Features Encoding for Unknown Attacks

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, finding solutions to prevent attacks in the fingerprint identification procedure is essential. This problem is usually addressed by analyzing whether a particular fingerprint sample stems from a live subject or an artificial replica [19]. Although this problem remains difficult in terms of robustness, effectiveness, and efficiency, several studies are still proposing hardware and software-based approaches [20], [21].…”

Section: Related Work: Fingerprint Identificationmentioning

confidence: 99%

Asynchronous Processing for Latent Fingerprint Identification on Heterogeneous CPU-GPU Systems

et al. 2020

View full text Add to dashboard Cite

Latent fingerprint identification is one of the most essential identification procedures in criminal investigations. Addressing this task is challenging as (i) it requires analyzing massive databases in reasonable periods and (ii) it is commonly solved by combining different methods with very complex datadependencies, which make fully exploiting heterogeneous CPU-GPU systems very complex. Most efforts in this context focus on improving the accuracy of the approaches and neglect reducing the processing time. Indeed, the most accurate approach was designed for one single thread. This work introduces ALFI (Asynchronous processing for Latent Fingerprint Identification), the fastest methodology for latent fingerprint identification maintaining high accuracy. ALFI fully exploits all the resources of CPU-GPU systems using asynchronous processing and fine-coarse parallelism for analyzing massive databases. Our approach reduces idle times in processing and fully exploits the inherent parallelism of comparing latent fingerprints to fingerprint impressions. We analyzed the performance of ALFI on Linux and Windows operating systems using the well-known NIST/FVC databases. Experimental results reveal that ALFI is in average 22x faster than the state-of-the-art algorithm, reaching a value of 44.7x for the best-studied case.

show abstract

“…In order to capture more information and thereby increase the descriptor distinctiveness, we compute the LBP patterns for various radii σ and number of neighbors N (i.e., σ = {1, 2, 3} and N = {8, 16, 24}), as in [6].…”

Section: A Local Binary Patternsmentioning

confidence: 99%

“…SVMs are popular as classifiers since they perform well in high-dimensional spaces and avoid over-fitting. In order to improve the generalisation capability of the analysed texture descriptors, we also utilise the Fisher Vector (FV) representation, which has shown remarkable results for unknown fingerprint [6] and face [7] PAD. By assuming that the unknown attacks share more texture, shape, and appearance features with known PAI species than with BP samples, the FV representation defines a common feature space from the parameters learned by an unsupervised Gaussian Mixture Model (GMM) in order to deal with the generalisation to unknown attacks.…”

Section: Introductionmentioning

confidence: 99%

Texture-based Presentation Attack Detection for Automatic Speaker Verification

Gonzalez-Soler¹,

Patino²,

Gomez‐Barrero³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Biometric systems are nowadays employed across a broad range of applications. They provide high security and efficiency and, in many cases, are user friendly. Despite these and other advantages, biometric systems in general and Automatic speaker verification (ASV) systems in particular can be vulnerable to attack presentations. The most recent ASVSpoof 2019 competition showed that most forms of attacks can be detected reliably with ensemble classifier-based presentation attack detection (PAD) approaches. These, though, depend fundamentally upon the complementarity of systems in the ensemble. With the motivation to increase the generalisability of PAD solutions, this paper reports our exploration of texture descriptors applied to the analysis of speech spectrogram images. In particular, we propose a common fisher vector feature space based on a generative model. Experimental results show the soundness of our approach: at most, 16 in 100 bona fide presentations are rejected whereas only one in 100 attack presentations are accepted.

show abstract

On the Impact of Different Fabrication Materials on Fingerprint Presentation Attack Detection

Cited by 13 publications

References 18 publications

Fingerprint Presentation Attack Detection Based on Local Features Encoding for Unknown Attacks

Fingerprint Presentation Attack Detection Based on Local Features Encoding for Unknown Attacks

Asynchronous Processing for Latent Fingerprint Identification on Heterogeneous CPU-GPU Systems

Texture-based Presentation Attack Detection for Automatic Speaker Verification

Contact Info

Product

Resources

About