Logo des Repositoriums

P296 - BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group

https://dl.gi.de/handle/20.500.12116/34220
Auflistung nach:

Auflistung P296 - BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group nach Autor:in "Brömme, Arslan"

1 - 10 von 23
  • Konferenzbeitrag
    Adversarial learning for a robust iris presentation attack detection method against unseen attack presentations
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Ferreira, Pedro M.; Sequeira, Ana F.; Pernes, Diogo; Rebelo, Ana; Cardoso, Jaime S.
    Despite the high performance of current presentation attack detection (PAD) methods, the robustness to unseen attacks is still an under addressed challenge. This work approaches the problem by enforcing the learning of the bona fide presentations while making the model less dependent on the presentation attack instrument species (PAIS). The proposed model comprises an encoder, mapping from input features to latent representations, and two classifiers operating on these underlying representations: (i) the task-classifier, for predicting the class labels (as bona fide or attack); and (ii) the species-classifier, for predicting the PAIS. In the learning stage, the encoder is trained to help the task-classifier while trying to fool the species-classifier. Plus, an additional training objective enforcing the similarity of the latent distributions of different species is added leading to a ‘PAIspecies’- independent model. The experimental results demonstrated that the proposed regularisation strategies equipped the neural network with increased PAD robustness. The adversarial model obtained better loss and accuracy as well as improved error rates in the detection of attack and bona fide presentations.
  • Konferenzbeitrag
    Android Pattern Unlock Authentication - effectiveness of local and global dynamic features
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Ibrahim, Nasiru; Sellahewa, Harin
    This study conducts a holistic analysis of the performances of biometric features incorporated into Pattern Unlock authentication. The objective is to enhance the strength of the authentication by adding an implicit layer. Earlier studies have incorporated either global or local dynamic features for verification; however, as found in this paper, different features have variable discriminating power, especially at different extraction levels. The discriminating potential of global, local and their combination are evaluated. Results showed that locally extracted features have higher discriminating power than global features and combining both features gives the best verification performance. Further, a novel feature was proposed and evaluated, which was found to have a varied impact (both positive and negative) on the system performance. From our findings, it is essential to evaluate features (independently and collectively), extracted at different levels (global and local) and different combination for some might impede on the verification performance of the system.
  • Konferenzbeitrag
    Anomalies in measuring speed and other dynamic properties with touchscreens and tablets
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Griechisch, Erika; Ward, Jean Renard; Hanczár, Gergely
    Touchscreens and tablets are often used in different studies and applications to capture high-resolution drawing, handwriting, or signatures. Several studies tend to analyse different properties, such as peaks or changes of the time derivatives of the coordinates; like velocity, angular velocity, acceleration or jerk of the movements. These are substantial features to analyse drawing, analyse or recognize handwriting, to examine the fluency of handwriting or verify signatures. The reliability of such a study strongly depends on the fidelity of the acquired data. We have tested several touchscreens and tablets which are widely used in different research studies, focusing on the resolution and accuracy of the coordinates and the uniformity of sampling. We have found that the vendors’ performance specifications (to the extent the vendor gives meaningful specifications) may seriously deviate from reality. Even if some of the raw data may look satisfactory at first sight, our examination uncovered several potentially significant bad behaviors, and instances in which the specifications from the vendors are, at best, misleading and incompletely informative. Some authors mention that the reliability of tablet data is unclear [Ha13, Fr05], but researchers may underestimate to what extent it could influence their results. This paper uncovers some aspects of the unreliability of the data and emphasizes the importance of understanding and addressing (or at least, knowing) the revealed problems prior to any analysis.
  • Konferenzbeitrag
    BIOSIG 2019 - Komplettband
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019)
  • Konferenzbeitrag
    Decoupling texture blending and shape warping in face morphing
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Matteo Ferrara, Matteo; Franco, Annalisa; Maltoni, Davide
    Automatic face recognition systems (FRS) are quite sensitive to the well-known face morphing attack, as pointed out by several researchers. Considering that, in the perspective of a fraudulent document usage, a criminal would certainly do its best to fool both humans and FRSs, the design of effective countermeasures should consider the trickiest and challenging conditions. Cognitive studies show that facial texture and shape (the two main components modified by face morphing) play a different role in face recognition by humans. This paper aims at understanding the behavior of FRSs with respect to these two factors and to identify the morphing parameters that maximize the probability of a successful attack
  • Konferenzbeitrag
    Deep Domain Adaption for Convolutional Neural Network (CNN) based Iris Segmentation: Solutions and Pitfalls
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Jalilian, Ehsaneddin; Uhl, Andreas
    Addressing the lack of massive amounts of labeled training data, deep domain adaptation has been applied successfully in many applications of machine learning. We investigate the application of deep domain adaptation for CNN based iris segmentation, exploring available solutions and their corresponding strengths and pitfalls, with several major contributions. First, we provide a comprehensive survey of current deep domain adaptation methods according to the properties of data that cause the domains divergence. Second, after selecting credible methods, we evaluate their expedience in terms of iris segmentation performance. Third, we analyze and compare the performance against the state-of-the-art methods under these categories. Forth, potential shortfalls of current methods and several future directions are pointed out and discussed.
  • Konferenzbeitrag
    Development of 2,400ppi Fingerprint Sensor for Capturing Neonate Fingerprint within 24 Hours after Birth
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Koda, Yoshinori; Takahashi, Ai; Ito, Koichi; Aoki, Takafumi; Kaneko, Satoshi; Nzou, Samson Muuo
    United Nations adopted the resolution “Sustainable Development Goals (SDGs),” which aims at solving the eradicating the poverty in all its forms and dimensions. One of the action plans is listed at “Goal 16 Target 16.9,” which clearly directs “By 2030, provide legal identity for all, including birth registration.” A fingerprint identification technology is one of the best solutions from the viewpoint of making a reliable identification system for the birth registration. However, collecting the fingerprint data from neonates is currently considered as one of the most difficult technology areas. Addressing this problem, we develop a novel high-resolution fingerprint sensor, whose image resolution is 2,400ppi. We collect fingerprint images from neonates within 24 hours after birth through the field research in Kenya. The experiments using our dataset demonstrates the effectiveness of our fingerprint sensor in neonate identification compared with 500ppi and 1,270ppi fingerprint sensors.
  • Konferenzbeitrag
    Fast and Accurate Continuous User Authentication by Fusion of Instance-based, Free-text Keystroke Dynamics
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Ayotte, Blaine; Banavar, Mahesh K.; Hou, Daqing; Schuckers, Stephanie
    Keystroke dynamics study the way in which users input text via their keyboards, which is unique to each individual, and can form a component of a behavioral biometric system to improve existing account security. Keystroke dynamics systems on free-text data use n-graphs that measure the timing between consecutive keystrokes to distinguish between users. Many algorithms require 500, 1,000, or more keystrokes to achieve EERs of below 10%. In this paper, we propose an instancebased graph comparison algorithm to reduce the number of keystrokes required to authenticate users. Commonly used features such as monographs and digraphs are investigated. Feature importance is determined and used to construct a fused classifier. Detection error tradeoff (DET) curves are produced with different numbers of keystrokes. The fused classifier outperforms the state-of-the-art with EERs of 7.9%, 5.7%, 3.4%, and 2.7% for test samples of 50, 100, 200, and 500 keystrokes.
  • Konferenzbeitrag
    Fingerprint Pre-Alignment based on Deep Learning
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Dieckmann, Benjamin; Merkle, Johannes; Rathgeb, Christian
    Robust fingerprint pre-alignment is vital for identification systems and biometric cryptosystems based on fingerprint minutiae, where computation of a relative alignment by comparison of the fingerprints is inefficient or intractable, respectively. The pre-alignment is achieved through an absolute alignment, i. e. an alignment computed for each fingerprint independently, which can be applied for fingerprint registration to compensate for variations in the placement (translation) and rotation of the fingerprints prior to their comparison. In this work, a deep learning approach for absolute pre-alignment of fingerprints is presented. The proposed algorithm employs a siamese network (with CNNs as subnetworks) which is trained on synthetically generated fingerprints using horizontal/vertical translation and rotation as three regression coefficients. Evaluations are conducted on the FVC2000 DB2a and the MCYT fingerprint database. Compared to other published fingerprint pre-alignment methods, the presented scheme achieves higher accuracy w. r. t. rotation estimation and overall robustness. In addition, the proposed pre-alignment is applied as a pre-processing step in a Fuzzy Vault scheme.
  • Konferenzbeitrag
    Gait verification using deep learning with a pairwise loss
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Yalavarthi, Vijaya Krishna; Grabocka, Josif; Mandalapu, Hareesh; Schmidt-Thieme, Lars
    A unique walking pattern to every individual makes gait a promising biometric. Gait is becoming an increasingly important biometric because it can be captured non-intrusively through accelerometers positioned at various locations on the human body. The advent of wearable sensors technology helps in collecting the gait data seamlessly at a low cost. Thus gait biometrics using accelerometers play significant role in security-related applications like identity verification and recognition. In this work, we deal with the problem of identity verification using gait. As the data received through the sensors is indexed in time order, we consider identity verification through gait data as the time series binary classification problem. We present deep learning model with a pairwise loss function for the classification.We conducted experiments using two datasets: publicly available ZJU dataset of more than 150 subjects and our self collected dataset with 15 subjects. With our model, we obtained an Equal Error Rate of 0.05% over ZJU dataset and 0.5% over our dataset which shows that our model is superior to the state-of-the-art baselines.