Logo des Repositoriums

Auflistung nach Autor:in "Sequeira, Ana F."

1 - 10 von 39
  • 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
    Assessing the Human Ability to Recognize Synthetic Speech in Ordinary Conversation
    (BIOSIG 2023, 2023) Daniel Prudký, Anton Firc
    This work assesses the human ability to recognize synthetic speech (deepfake). This paper describes an experiment in which we communicated with respondents using voice messages. We presented the respondents with a cover story about testing the user-friendliness of voice messages while secretly sending them a pre-prepared deepfake recording during the conversation. We examined their reactions, knowledge of deepfakes, or how many could correctly identify which message was deepfake. The results show that none of the respondents reacted in any way to the fraudulent deepfake message, and only one retrospectively admitted to noticing something specific. On the other hand, a voicemail message that contained a deepfake was correctly identified by 83.9% of respondents after revealing the nature of the experiment. Thus, the results show that although the deepfake recording was clearly identifiable among others, no one reacted to it. In summary, we show that the human ability to recognize voice deepfakes is not at a level we can trust. It is very difficult for people to distinguish between real and fake voices, especially if they do not expect them.
  • Konferenzbeitrag
    Automatic validation of ICAO compliance regarding head coverings: an inclusive approach concerning religious circumstances
    (BIOSIG 2023, 2023) Carla Guerra, João S. Marcos
    This paper contributes with a dataset and an algorithm that automatically verifies the compliance with the ICAO requirements related to the use of head coverings on facial images used on machine-readable travel documents. All the methods found in the literature ignore that some coverings might be accepted because of religious or cultural reasons, and basically only look for the presence of hats/caps. Our approach specifically includes the religious cases and distinguishes the head coverings that might be considered compliant. We built a dataset composed by facial images of 500 identities to accommodate these type of accessories. That data was used to fine-tune and train a classification model based on the YOLOv8 framework and we achieved state of the art results with an accuracy of 99.1% and EER of 5.7%.
  • Konferenzbeitrag
    Benchmarking fixed-length Fingerprint Representations across different Embedding Sizes and Sensor Types
    (BIOSIG 2023, 2023) Tim Rohwedder, Daile Osorio Roig
    Traditional minutiae-based fingerprint representations consist of a variable-length set of minutiae. This necessitates a more complex comparison causing the drawback of high computational cost in one-to-many comparison. Recently, deep neural networks have been proposed to extract fixed-length embeddings from fingerprints. In this paper, we explore to what extent fingerprint texture information contained in such embeddings can be reduced in terms of dimension, while preserving high biometric performance. This is of particular interest, since it would allow to reduce the number of operations incurred at comparisons. We also study the impact in terms of recognition performance of the fingerprint textural information for two sensor types, i.e. optical and capacitive. Furthermore, the impact of rotation and translation of fingerprint images on the extraction of fingerprint embeddings is analysed. Experimental results conducted on a publicly available database reveal an optimal embedding size of 512 feature elements for the texture-based embedding part of fixed-length fingerprint representations. In addition, differences in performance between sensor types can be perceived. The source code of all experiments presented in this paper is publicly available at https://github.com/tim-rohwedder/fixed-length-fingerprint-extractors, so our work can be fully reproduced.
  • Konferenzbeitrag
    BIOSIG 2023 - Complete Volume
    (BIOSIG 2023, 2023)
  • Konferenzbeitrag
    Comparison of two architectures for text-independent verification after character-unaware text segmentation
    (BIOSIG 2023, 2023) Maria De Marsico, Mohammadreza Shabani
    This paper compares the performance of two popular CNN architectures, ResNet-50 and MobileNetV2, fine-tuned for text-independent writer verification. The used benchmark is IAM dataset. The further contributions are an easy and fast sub-region cropping for robust model training, and a biometrics-oriented performance evaluation. The preliminary results are encouraging.
  • Konferenzbeitrag
    Compressed Models Decompress Race Biases: What Quantized Models Forget for Fair Face Recognition
    (BIOSIG 2023, 2023) Pedro C. Neto, Eduarda Caldeira
    With the ever-growing complexity of deep learning models for face recognition, it becomes hard to deploy these systems in real life. Researchers have two options: 1) use smaller models; 2) compress their current models. Since the usage of smaller models might lead to concerning biases, compression gains relevance. However, compressing might be also responsible for an increase in the bias of the final model. We investigate the overall performance, the performance on each ethnicity subgroup and the racial bias of a State-of-the-Art quantization approach when used with synthetic and real data. This analysis provides a few more details on potential benefits of performing quantization with synthetic data, for instance, the reduction of biases on the majority of test scenarios. We tested five distinct architectures and three different training datasets. The models were evaluated on a fourth dataset which was collected to infer and compare the performance of face recognition models on different ethnicity.
  • Konferenzbeitrag
    Contactless Fingerprints: Differential Performance for Fingers of Varying Size and Ridge Density
    (BIOSIG 2023, 2023) Carson King, Evan Garrett
    The match performance of contactless fingerprint probes compared to contact-based galleries has increased accuracy. This performance, along with convenience of use, is encouraging the utilization of contactless fingerprint collection methods. However, issues with differential performance for different demographics may still exist. Past works focused mainly on the interoperability of contactless prints with smartphone applications and kiosk devices. This paper focuses on the differential performance of genuine match scores based on the demographic of finger size, ridge density, and total ridge count. Distribution of genuine match scores shows a correlation between an increase in genuine match scores and these variables in contactless smartphone collection methods with the largest correlation appearing in finger size.
  • Konferenzbeitrag
    Contactless Palmprint Recognition for Children
    (BIOSIG 2023, 2023) Akash M Godbole, Steven A Grosz
    Effective distribution of nutritional and healthcare aid for children, particularly infants and toddlers, in the world’s least developed and most impoverished countries, is a major problem due to lack of reliable identification documents. We present a mobile based contactless palmprint recognition system, Child Palm-ID, which meets the requirements of usability, cost, and accuracy for child recognition. On a contactless child palmprint database, Child-PalmDB1, with 1,020 unique palms (age range of 6 mos. to 48 mos.), Child Palm-ID achieves a TAR=94.8% at FAR=0.1%. Child Palm-ID is also able to recognize adults, achieving a TAR=99.5% on the CASIA contactless palmprint database and a TAR=100% on the COEP contactless adult palmprint database, both at FAR=0.1%. For child palmprint images captured at an interval of five months with differences in standoff distance, illumination and motion blur, the TAR drops to 80.5% at FAR=0.1%. This indicates that more research remains in contactless child palmprint recognition.
  • Konferenzbeitrag
    Cross-eyed - cross-spectral iris/periocular recognition database and competition
    (Biosig 2016, 2016) Sequeira, Ana F.; Chen, Lulu; Ferryman, James; Alonso-Fernandez, Fernando; Bigun, Josef; Raja, Kiran B.; Ramachandra, Raghavendra; Busch, Christoph; Wild, Peter