Fingerphoto Presentation Attack Detection: Generalization in Smartphones

Marasco, Emanuela; Vurity, Anudeep

doi:10.1109/bigdata52589.2021.9672054

Cited by 14 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The more recent research was focused on CNNs for PAD purposes. Here, CNNs for general purpose object detection are fine-tuned for the special PAD task, like proposed by Fujio et al [4] and Marasco and Vurity [31]. The proposals process the fingerprint samples in various ways in order to maximize detection accuracy.…”

Section: Pad Algorithmsmentioning

confidence: 99%

Mobile Contactless Fingerprint Presentation Attack Detection: Generalizability and Explainability

Priesnitz,

Casula,

Kolberg

et al. 2024

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

Contactless fingerprint recognition is an emerging biometric technology that has several advantages over contact-based schemes, such as improved user acceptance and fewer hygienic concerns. Like for most other biometrics, Presentation Attack Detection (PAD) is crucial to preserving the trustworthiness of contactless fingerprint recognition methods. For many contactless biometric characteristics, Convolutional Neural Networks (CNNs) represent the state-of-the-art of PAD algorithms. For CNNs, the ability to accurately classify samples that are not included in the training is of particular interest, since these generalization capabilities indicate robustness in real-world scenarios. In this work, we focus on the generalizability and explainability aspects of CNN-based contactless fingerprint PAD methods. Based on previously obtained findings, we selected four CNN-based methods for contactless fingerprint PAD: two PAD methods designed for other biometric characteristics, an algorithm for contact-based fingerprint PAD and a general-purpose ResNet18. For our evaluation, we use four databases and partition them using Leave-One-Out (LOO) protocols. Furthermore, the generalization capability to a newly captured database is tested. Moreover, we explore t-SNE plots as a means of explainability to interpret our results in more detail. The low D-EERs obtained from the LOO experiments (below 0.1% D-EER for every LOO group) indicate that the selected algorithms are well-suited for the particular application. However, with an D-EER of 4.14%, the generalization experiment still has room for improvement.

show abstract

Section: Pad Algorithmsmentioning

confidence: 99%

Mobile Contactless Fingerprint Presentation Attack Detection: Generalizability and Explainability

Priesnitz,

Casula,

Kolberg

et al. 2024

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

show abstract

“…The authors resized the images to 256*256 dimensions for analysis, which raise the chance of loss of further features in the unfocused dataset and might not provide a good classification against high-quality spoofs. The same PAD dataset, along with collected replay attack data, was used by Marasco et al [7] to achieve D-EER of 2.14% for AlexNet and 0.97% with ResNet. The authors evaluated different color spaces and CNN architectures, however, the publication did not mention the details of the image quality used for analysis.…”

Section: State-of-the-artmentioning

confidence: 99%

“…A smartphone camera can capture finger-photo and associated software can extract the necessary information from the photos to use it as an authentication technology. However, PAIs or spoofs can cause a security risk to the noncontact-based fingerprint systems and cause a breach of confidentiality or sensitive data leakage [6] [7]. So, it would be important to determine their ability to detect liveness.…”

Section: Introductionmentioning

confidence: 99%

Presentation Attack Detection with Advanced CNN Models for Noncontact-based Fingerprint Systems

Purnapatra¹,

Conor²,

Miner³

et al. 2023

Preprint

View full text Add to dashboard Cite

Touch-based fingerprint biometrics is one of the most popular biometric modalities with applications in several fields. Problems associated with touch-based techniques such as the presence of latent fingerprints and hygiene issues due to many people touching the same surface motivated the community to look for non-contact-based solutions. For the last few years, contactless fingerprint systems are on the rise and in demand because of the ability to turn any device with a camera into a fingerprint reader. Yet, before we can fully utilize the benefit of noncontact-based methods, the biometric community needs to resolve a few concerns such as the resiliency of the system against presentation attacks. One of the major obstacles is the limited publicly available data sets with inadequate spoof and live data. In this publication, we have developed a Presentation attack detection (PAD) dataset of more than 7500 four-finger images and more than 14,000 manually segmented single-fingertip images, and 10,000 synthetic fingertips (deepfakes). The PAD dataset was collected from six different Presentation Attack Instruments (PAI) of three different difficulty levels according to FIDO protocols, with five different types of PAI materials, and different smartphone cameras with manual focusing. We have utilized DenseNet-121 and NasNetMobile models and our proposed dataset to develop PAD algorithms and achieved PAD accuracy of Attack presentation classification error rate (APCER) 0.14% and Bonafide presentation classification error rate (BPCER) 0.18%. We have also reported the test results of the models against unseen spoof types to replicate uncertain real-world testing scenarios.

show abstract

“…Each of these characteristics can provide a significant level of importance. However, recent studies have emphasized the fingerphoto as a significant biometric [13][14][15][16] . It basically refers to a fingerprint that is taken by a smart phone, with no direct touching (contactless).…”

Section: Introductionmentioning

confidence: 99%

التحقق من البشر بواسطة تبني شبكة تعلم عميق لصور بصمات الاصابع

Alabdoo,

Yalçınkaya

2024

Baghdad Sci.J

View full text Add to dashboard Cite

يمكن اعتبار صورة الإصبع واحدة من أحدث وأكثر التقنيات البيومترية إثارة للاهتمام. يعني ذلك ببساطة صورة بصمة أصبع يتم الحصول عليها عن طريق هاتف ذكي بطريقة لا تتطلب الاتصال المباشر. يقترح هذا البحث نهجًا جديدًا للتحقق من البشر استنادًا إلى صورة الإصبع الفوتوغرافية. يُطلق عليه اسم شبكة الإصبع الفوتوغرافية العميقة المتكررة. تتألف من طبقة الإدخال، وسلسلة من الطبقات الخفية، وطبقة الإخراج والتغذية العكسية الاساسية. يعتمد هذا البحث على اخذ صور فوتوغرافية لكافة الاصابع الشخصية بشكل متسلسل. و يتمتع النظام بالقدرة على التبديل بين أوزان كل إصبع فوتوغرافي فردي وتوفير التحقق. تم انشاء قاعدة بينات من عدد كبير من صور الأصابع الفوتوغرافية، وتم تنظيمها وتقسيمها واستخدامها كمجموعة بيانات مفيدة في هذا البحث. تم التوصل الى نتائج عالية في الدقة في التحقق الشخصي عن طريق استخدام الصور الفوتوغرافية للاصابع.

show abstract

Fingerphoto Presentation Attack Detection: Generalization in Smartphones

Cited by 14 publications

References 13 publications

Mobile Contactless Fingerprint Presentation Attack Detection: Generalizability and Explainability

Mobile Contactless Fingerprint Presentation Attack Detection: Generalizability and Explainability

Presentation Attack Detection with Advanced CNN Models for Noncontact-based Fingerprint Systems

التحقق من البشر بواسطة تبني شبكة تعلم عميق لصور بصمات الاصابع

Contact Info

Product

Resources

About