Logo des Repositoriums

Auflistung nach Schlagwort "face recognition"

1 - 10 von 10
  • Konferenzbeitrag
    An anomaly detection approach for backdoored neural networks: face recognition as a case study
    (BIOSIG 2022, 2022) Alexander Unnervik and Sébastien Marcel
    Backdoor attacks allow an attacker to embed functionality jeopardizing proper behavior of any algorithm, machine learning or not. This hidden functionality can remain inactive for normal use of the algorithm until activated by the attacker. Given how stealthy backdoor attacks are, consequences of these backdoors could be disastrous if such networks were to be deployed for applications as critical as border or access control. In this paper, we propose a novel backdoored network detection method based on the principle of anomaly detection, involving access to the clean part of the training data and the trained network.We highlight its promising potential when considering various triggers, locations and identity pairs, without the need to make any assumptions on the nature of the backdoor and its setup. We test our method on a novel dataset of backdoored networks and report detectability results with perfect scores.
  • Konferenzbeitrag
    Can Generative Colourisation Help Face Recognition?
    (BIOSIG 2020 - Proceedings of the 19th International Conference of the Biometrics Special Interest Group, 2020) Drozdowski, Pawel; Fischer, Daniel; Rathgeb, Christian; Geissler, Julian; Knedlik, Jan; Busch, Christoph
    Generative colourisation methods can be applied to automatically convert greyscale images to realistically looking colour images. In a face recognition system, such techniques might be employed as a pre-processing step in scenarios where either one or both face images to be compared are only available in greyscale format. In an experimental setup which reflects said scenarios, we investigate if generative colourisation can improve face sample utility and overall biometric performance of face recognition. To this end, subsets of the FERET and FRGCv2 face image databases are converted to greyscale and colourised applying two versions of the DeOldify colourisation algorithm. Face sample quality assessment is done using the FaceQnet quality estimator. Biometric performance measurements are conducted for the widely used ArcFace system with its built-in face detector and reported according to standardised metrics. Obtained results indicate that, for the tested systems, the application of generative colourisation does neither improve face image quality nor recognition performance. However, generative colourisation was found to aid face detection and subsequent feature extraction of the used face recognition system which results in a decrease of the overall false reject rate.
  • Textdokument
    De-duplication using automated face recognition: a mathematical model and all babies are equally cute
    (BIOSIG 2017, 2017) Spreeuwers,Luuk
    De-duplication is defined as the technique to eliminate or link duplicate copies of repeating data. We consider a specific de-duplication application where a subject applies for a new passport and we want to check if he possesses a passport already under another name. To determine this, a facial photograph of the subject is compared to all photographs of the national database of passports.We investigate if state of the art facial recognition is up to this task and find that for a large database about 2 out of 3 duplicates can be found while few or no false duplicates are reported. This means that de-duplication using automated face recognition is feasible in practice.We also present a mathematical model to predict the performance of de-duplication and find that the probability that k false duplicates are returned can be described well by a Poisson distribution using a varying, subject specific false match rate. We present experimental results using a large database of actual passport photographs consisting of 224 000 images of about 100 000 subjects and find that the results are predicted well by our model.
  • Konferenzbeitrag
    Evaluating Face Image Quality Score Fusion for Modern Deep Learning Models
    (BIOSIG 2022, 2022) Schlett, Torsten; Rathgeb, Christian; Tapia, Juan E.; Busch, Christoph
    Face image quality assessment algorithms attempt to estimate the utility of face images for biometric systems, typically face recognition, since the performance of these systems can be limited by the image quality. Hand-crafted quality score fusion has previously been examined for a variety of mostly factor-specific quality assessment algorithms. This paper instead examines score fusion for various recent “monolithic” quality assessment deep learning models. The evaluation methodology is based on Error-versus-Reject-Characteristic partial-Area-Under-Curve values, which are used to quantitatively rank quality assessment configurations in a face recognition context. Mean quality score fusion configurations were found to slightly improve performance on the TinyFace database, while the tested fusion types were ineffective on the LFW database.
  • Konferenzbeitrag
    Impact of Doppelgängers on Face Recognition: Database and Evaluation
    (BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group, 2021) Rathgeb, Christian; Drozdowski, Pawel; Obel, Marcel; Dörsch, André; Stockhardt, Fabian; Haryanto, Nathania E.; Bernardo, Kevin; Busch, Christoph
    Look-alikes, a.k.a. doppelgängers, increase the probability of false matches in a facial recognition system, in contrast to random face image pairs selected for non-mated comparison trials. In order to analyse and improve the robustness of automated face recognition, datasets of doppelgänger face image pairs are needed. In this work, we present a new face database consisting of 400 pairs of doppelgänger images. Subsequently, two state-of-the-art face recognition systems are evaluated on said database and other public datasets, including the Disguised Faces in The Wild (DFW) database. It is found that the collected image pairs yield very high similarity scores resulting in a significant increase of false match rates. To facilitate reproducible research and future experiments in this field, the dataset is made available.
  • Konferenzbeitrag
    Improved Post-quantum-secure Face Template Protection System Based on Packed Homomorphic Encryption
    (BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group, 2021) Tamiya, Hiroto; Isshiki, Toshiyuki; Mori, Kengo; Obana, Satoshi; Ohki, Tetsushi
    This paper proposes an efficient face template protection system based on homomorphic encryption. By developing a message packing method suitable for the calculation of the square Euclidean distance, the proposed system computes the squared Euclidean distance between facial features by a single homomorphic multiplication. Our experimental results show the transaction time of the proposed system is about 14 times faster than that of the existing face template protection system based on homomorphic encryption presented in BIOSIG2020.
  • Konferenzbeitrag
    Model-Free Template Reconstruction Attack with Feature Converter
    (BIOSIG 2022, 2022) Muku Akasaka, Yuya Sato
    State-of-the-art template reconstruction attacks assume that an adversary has access to a part or whole of the functionality of a target model. However, in a practical scenario, rigid protection of the target system prevents them from gaining knowledge of the target model. In this paper, we propose a novel template reconstruction attack method utilizing a feature converter. The feature converter enables an adversary to reconstruct an image from a corresponding compromised template without knowledge about the target model. The proposed method was evaluated with qualitative and quantitative measures. We achieved the Successful Attack Rate(SAR) of 0.90 on Labeled Faces in the Wild Dataset(LFW) with compromised templates of only 1280 identities.
  • Konferenzbeitrag
    On the assessment of face image quality based on handcrafted features
    (BIOSIG 2020 - Proceedings of the 19th International Conference of the Biometrics Special Interest Group, 2020) Henniger, Olaf; Fu, Biying; Chen, Cong
    This paper studies the assessment of the quality of face images, predicting the utility of face images for automated recognition. The utility of frontal face images from a publicly available dataset was assessed by comparing them with each other using commercial off-the-shelf face recognition systems. Multiple face image features delineating face symmetry and characteristics of the capture process were analysed to find features predictive of utility. The selected features were used to build system-specific and generic random forest classifiers.
  • Konferenzbeitrag
    QualFace: Adapting Deep Learning Face Recognition for ID and Travel Documents with Quality Assessment
    (BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group, 2021) Tremoço, João; Medvedev, Iurii; Gonçalves, Nuno
    Modern face recognition biometrics widely rely on deep neural networks that are usually trained on large collections of wild face images of celebrities. This choice of the data is related with its public availability in a situation when existing ID document compliant face image datasets (usually stored by national institutions) are hardly accessible due to continuously increasing privacy restrictions. However this may lead to a leak in performance in systems developed specifically for ID document compliant images. In this work we proposed a novel face recognition approach for mitigating that problem. To adapt deep face recognition network for document security purposes, we propose to regularise the training process with specific sample mining strategy which penalises the samples by their estimated quality, where the quality metric is proposed by our work and is related to the specific case of face images for ID documents. We perform extensive experiments and demonstrate the efficiency of proposed approach for ID document compliant face images.
  • Konferenzbeitrag
    Transferability Analysis of an Adversarial Attack on Gender Classification to Face Recognition
    (BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group, 2021) Rezgui, Zohra; Bassit, Amina
    Modern biometric systems establish their decision based on the outcome of machine learning (ML) classifiers trained to make accurate predictions. Such classifiers are vulnerable to diverse adversarial attacks, altering the classifiers' predictions by adding a crafted perturbation. According to ML literature, those attacks are transferable among models that perform the same task. However, models performing different tasks, but sharing the same input space and the same model architecture, were never included in transferability scenarios. In this paper, we analyze this phenomenon for the special case of VGG16-based biometric classifiers. Concretely, we study the effect of the white-box FGSM attack, on a gender classifier and compare several defense methods as countermeasure. Then, in a black-box manner, we attack a pre-trained face recognition classifier using adversarial images generated by the FGSM. Our experiments show that this attack is transferable from a gender classifier to a face recognition classifier where both were independently trained.