Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Publicações

Publicações por João Tiago Pinto

2020

Secure Triplet Loss for End-to-End Deep Biometrics

Autores
Pinto, JR; Cardoso, JS; Correia, MV;

Publicação
2020 8TH INTERNATIONAL WORKSHOP ON BIOMETRICS AND FORENSICS (IWBF 2020)

Abstract
Although deep learning is being widely adopted for every topic in pattern recognition, its use for secure and cance-lable biometrics is currently reserved for feature extraction and biometric data preprocessing, limiting achievable performance. In this paper, we propose a novel formulation of the triplet loss methodology, designated as secure triplet loss, that enables biometric template cancelability with end-to-end convolutional neural networks, using easily changeable keys. Trained and evaluated for electrocardiogram-based biometrics, the network revealed easy to optimize using the modified triplet loss and achieved superior performance when compared with the state-of-the-art (10.63% equal error rate with data from 918 subjects of the UofTDB database). Additionally, it ensured biometric template security and effective template cancelability. Although further efforts are needed to avoid template linkability, the proposed secure triplet loss shows promise in template cancelability and non-invertibility for biometric recognition while taking advantage of the full power of convolutional neural networks.

2020

Weakly-Supervised Classification of HER2 Expression in Breast Cancer Haematoxylin and Eosin Stained Slides

Autores
Oliveira, SP; Pinto, JR; Goncalves, T; Canas Marques, R; Cardoso, MJ; Oliveira, HP; Cardoso, JS;

Publicação
APPLIED SCIENCES-BASEL

Abstract
Human epidermal growth factor receptor 2 (HER2) evaluation commonly requires immunohistochemistry (IHC) tests on breast cancer tissue, in addition to the standard haematoxylin and eosin (H&E) staining tests. Additional costs and time spent on further testing might be avoided if HER2 overexpression could be effectively inferred from H&E stained slides, as a preliminary indication of the IHC result. In this paper, we propose the first method that aims to achieve this goal. The proposed method is based on multiple instance learning (MIL), using a convolutional neural network (CNN) that separately processes H&E stained slide tiles and outputs an IHC label. This CNN is pretrained on IHC stained slide tiles but does not use these data during inference/testing. H&E tiles are extracted from invasive tumour areas segmented with the HASHI algorithm. The individual tile labels are then combined to obtain a single label for the whole slide. The network was trained on slides from the HER2 Scoring Contest dataset (HER2SC) and tested on two disjoint subsets of slides from the HER2SC database and the TCGA-TCIA-BRCA (BRCA) collection. The proposed method attained83.3%classification accuracy on the HER2SC test set and 53.8% on the BRCA test set. Although further efforts should be devoted to achieving improved performance, the obtained results are promising, suggesting that it is possible to perform HER2 overexpression classification on H&E stained tissue slides.

2020

Interpretable Biometrics: Should We Rethink How Presentation Attack Detection is Evaluated?

Autores
Sequeira, AF; Silva, W; Pinto, JR; Goncalves, T; Cardoso, JS;

Publicação
2020 8TH INTERNATIONAL WORKSHOP ON BIOMETRICS AND FORENSICS (IWBF 2020)

Abstract
Presentation attack detection (PAD) methods are commonly evaluated using metrics based on the predicted labels. This is a limitation, especially for more elusive methods based on deep learning which can freely learn the most suitable features. Though often being more accurate, these models operate as complex black boxes which makes the inner processes that sustain their predictions still baffling. Interpretability tools are now being used to delve deeper into the operation of machine learning methods, especially artificial networks, to better understand how they reach their decisions. In this paper, we make a case for the integration of interpretability tools in the evaluation of PAD. A simple model for face PAD, based on convolutional neural networks, was implemented and evaluated using both traditional metrics (APCER, BPCER and EER) and interpretability tools (Grad-CAM), using data from the ROSE Youtu video collection. The results show that interpretability tools can capture more completely the intricate behavior of the implemented model, and enable the identification of certain properties that should be verified by a PAD method that is robust, coherent, meaningful, and can adequately generalize to unseen data and attacks. One can conclude that, with further efforts devoted towards higher objectivity in interpretability, this can be the key to obtain deeper and more thorough PAD performance evaluation setups.

2019

An End-to-End Convolutional Neural Network for ECG-Based Biometric Authentication

Autores
Pinto, JR; Cardoso, JS;

Publicação
2019 IEEE 10TH INTERNATIONAL CONFERENCE ON BIOMETRICS THEORY, APPLICATIONS AND SYSTEMS (BTAS)

Abstract

2020

Self-Learning with Stochastic Triplet Loss

Autores
Pinto, JR; Cardoso, JS;

Publicação
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)

Abstract
Deep learning has offered significant performance improvements on several pattern recognition problems. However, the well-known need for large amounts of labeled data limits applicability and performance where those are not available. Hence, this paper proposes an adaptation of the triplet loss for self-learning with entirely unlabeled data, where there is uncertainty in the generated triplets. The methodology was applied to off-the-person electrocardiogram-based biometric authentication and unconstrained face identity verification tasks, including stress experiments designed to simulate more difficult circumstances. Despite the uncertainty related to the use of unlabeled data, the method was mostly capable of avoiding negatively affecting the model's performance. The promising results show the proposed method can be a viable alternative to supervised learning in cases where only unlabeled data are available. The method is especially suitable for training with continuous stream-based datasets such as on person re-identification in video streams and continuous electrocardiogram-based biometrics.

2020

Explaining ECG Biometrics: Is It All In The QRS?

Autores
Pinto, JR; Cardoso, JS;

Publicação
2020 INTERNATIONAL CONFERENCE OF THE BIOMETRICS SPECIAL INTEREST GROUP (BIOSIG)

Abstract
The literature seems to indicate that the QRS complex is the most important component of the electrocardiogram (ECG) for biometrics. To verify this claim, we use interpretability tools to explain how a convolutional neural network uses ECG signals to identify people, using on-the-person (PTB) and off-the-person (UofTDB) signals. While the QRS complex appears indeed to be a key feature on ECG biometrics, especially with cleaner signals, results indicate that, for larger populations in off-the-person settings, the QRS shares relevance with other heartbeat components, which it is essential to locate. These insights indicate that avoiding excessive focus on the QRS complex, using decision explanations during training, could be useful for model regularisation.

  • 2
  • 6