Logo des Repositoriums

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

Autor*innen mit den meisten Dokumenten  

Auflistung nach:

Neueste Veröffentlichungen

1 - 10 von 23
  • Konferenzbeitrag
    Perspective Multiplication for Multi-Perspective Enrolment in Finger Vein Recognition
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Prommegger, Bernhard; Uhl, Andreas
    Finger vein recognition deals with the identification of subjects based on their venous pattern within the fingers. It has been shown that its recognition accuracy heavily depends on a good alignment of the acquired samples. There are several approaches that try to reduce the impact of finger misplacement. However, none of this approaches is able to prevent all possible types of finger misplacements. As finger vein scanners are evolving towards contact-less acquisition, alignment problems, especially due to longitudinal finger rotation, are becoming even more important. One way to tackle this problem is capturing the vein structure from different perspectives during enrolment, but cost and complexity of capturing devices increases with the number of involved cameras. In this article, a new method to reduce the number of cameras needed for multi-perspective enrolment is presented. The reduction is achieved by introducing additional pseudo perspectives in-between two adjacent cameras. The obtained perspectives are used for additional comparisons during authentication. This way, the complexity of the enrolment devices can be reduced while keeping the recognition performance at a high level.
  • 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
    Is There Any Similarity Between a Person’s Left and Right Retina?
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Biswas, Sangeeta; Rohdin, Johan; Mňuk, Tomáš; Drahanský, Martin
    It is often argued among biometric researchers that the left and right retinas of the same person are as different as the retinas of two different persons. In this paper we investigate to what extent this is true. We perform experiments where human volunteers are asked to judge whether a pair of the left and right retinal images displayed side-by-side belongs to the same person or two different persons. We also use two similarity measurements, structural similarity (SSIM) and cosine similarity, to do the investigation process automatically. Our experiments show that there is recognizable similarity in the left and right retina of a person. For a verification task done by human volunteers, the average accuracy was 82%. For identification tasks, automatic systems using cosine similarity were correct in up to 57%.
  • 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
    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
    Style Your Face Morph and Improve Your Face Morphing Attack Detector
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Seibold, Clemens; Hilsmann, Anna; Eisert, Peter
    A morphed face image is a synthetically created image that looks so similar to the faces of two subjects that both can use it for verification against a biometric verification system. It can be easily created by aligning and blending face images of the two subjects. In this paper, we propose a style transfer based method that improves the quality of morphed face images. It counters the image degeneration during the creation of morphed face images caused by blending. We analyze different state of the art face morphing attack detection systems regarding their performance against our improved morphed face images and other methods that improve the image quality. All detection systems perform significantly worse, when first confronted with our improved morphed face images. Most of them can be enhanced by adding our quality improved morphs to the training data, which further improves the robustness against other means of quality improvement.
  • 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
    BIOSIG 2019 - Komplettband
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019)
  • 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
    Multi-resolution Local Descriptor for 3D Ear Recognition
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Ganapathi, Iyyakutti Iyappan; Ali, Syed Sadaf; Prakash, Surya
    Several approaches have shown promising results in human ear recognition. However, factors such as the pose, illumination, and scaling have an enormous impact on recognition performance. 3D models are insensitive to these factors and are found to be better at enhancing recognition performance with strong geometric information. Low cost 3D data acquisition has also boosted the research community in recent times to explore more about 3D object recognition. We present a local multi-resolution descriptor in this paper to recognize human ears in 3D. For each key-point in 3D ear, a local reference frame (LRF) is constructed. Using multi-radii, we find neighbors at each key-point and the neighbors obtained from each radius are projected to create a depth image using the LRF. Further, a descriptor is computed by employing neural network based auto-encoders and the local statistics of the depth images. The descriptor is used to locate the potential correspondence matching points in the probe and gallery images for a coarse arrangement, followed by a fine alignment to compute the registration error. The obtained registration error is used as the matching score. The proposed technique is assessed on UND-J2 dataset to demonstrate its effectiveness.