Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
About
Download Photo HD

About

Ana F. Sequeira holds a PhD in Electrical and Computing Engineering obtained from the Engineering Faculty of University of Porto, Portugal in 2015. Ana also holds a Master degree in Mathematical Engineering and a 5-years degree in Mathematics, both obtained from the Mathematics Department of the Science Faculty of the University Of Porto, Portugal.

Ana collaborated as a researcher at INESC TEC, a R&D institute affiliated to the University of Porto, within the Visual Computing and Machine Intelligence Group (VCMI) during her PhD studies.

Ana’s PhD studies, in the fields of computer vision and machine learning, focused on liveness detection techniques for iris and fingerprint. This research equipped Ana with a deep knowledge and diversified skills regarding the complete image processing and classification pipeline: from the pre-processing methods to the classification/decision step passing through the application of feature extraction techniques.

The post-doctoral research was pursued at the University of Reading, UK, collaborating in EU projects related to the application of biometric recognition in Border Control (FASTPASS and PROTECT projects).

This activity was followed by a short term collaboration with the company Iris Guard UK in order to research on the vulnerabilities of EyePay® technology’s to spoofing and to develop a proof-of-concept of an anti-spoofing measure.

Currently, Ana is back at INESC TEC as a Research Assistant.

During Ana’s activity as PhD and PDRA, she authored and co-authored several research publications in major international conferences and journals which attracted, to the date, over 150 citations.

Throughout her research activity, Ana developed expertise not only in computer vision/image processing topics but as well in the application of diversified machine learning techniques, from classic to deep learning methodologies.

Interest
Topics
Details

Details

002
Publications

2022

Myope Models - Are face presentation attack detection models short-sighted?

Authors
Neto, PC; Sequeira, AF; Cardoso, JS;

Publication
2022 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW 2022)

Abstract

2022

Editorial of the Special Issue from WorldCIST'20

Authors
Domingues, I; Sequeira, AF;

Publication
COMPUTATIONAL AND MATHEMATICAL ORGANIZATION THEORY

Abstract

2022

Beyond Masks: On the Generalization of Masked Face Recognition Models to Occluded Face Recognition

Authors
Neto, PCP; Pinto, JR; Boutros, F; Damer, N; Sequeira, AF; Cardoso, JS;

Publication
IEEE ACCESS

Abstract

2021

Maximum Relevance Minimum Redundancy Dropout with Informative Kernel Determinantal Point Process

Authors
Saffari, M; Khodayar, M; Saadabadi, MSE; Sequeira, AF; Cardoso, JS;

Publication
SENSORS

Abstract
In recent years, deep neural networks have shown significant progress in computer vision due to their large generalization capacity; however, the overfitting problem ubiquitously threatens the learning process of these highly nonlinear architectures. Dropout is a recent solution to mitigate overfitting that has witnessed significant success in various classification applications. Recently, many efforts have been made to improve the Standard dropout using an unsupervised merit-based semantic selection of neurons in the latent space. However, these studies do not consider the task-relevant information quality and quantity and the diversity of the latent kernels. To solve the challenge of dropping less informative neurons in deep learning, we propose an efficient end-to-end dropout algorithm that selects the most informative neurons with the highest correlation with the target output considering the sparsity in its selection procedure. First, to promote activation diversity, we devise an approach to select the most diverse set of neurons by making use of determinantal point process (DPP) sampling. Furthermore, to incorporate task specificity into deep latent features, a mutual information (MI)-based merit function is developed. Leveraging the proposed MI with DPP sampling, we introduce the novel DPPMI dropout that adaptively adjusts the retention rate of neurons based on their contribution to the neural network task. Empirical studies on real-world classification benchmarks including, MNIST, SVHN, CIFAR10, CIFAR100, demonstrate the superiority of our proposed method over recent state-of-the-art dropout algorithms in the literature.

2021

MFR 2021: Masked Face Recognition Competition

Authors
Boutros, F; Damer, N; Kolf, JN; Raja, K; Kirchbuchner, F; Ramachandra, R; Kuijper, A; Fang, P; Zhang, C; Wang, F; Montero, D; Aginako, N; Sierra, B; Nieto, M; Erakin, ME; Demir, U; Ekenel, HK; Kataoka, A; Ichikawa, K; Kubo, S; Zhang, J; He, M; Han, D; Shan, S; Grm, K; Struc, V; Seneviratne, S; Kasthuriarachchi, N; Rasnayaka, S; Neto, PC; Sequeira, AF; Pinto, JR; Saffari, M; Cardoso, JS;

Publication
International IEEE Joint Conference on Biometrics, IJCB 2021, Shenzhen, China, August 4-7, 2021

Abstract

Supervised
thesis

2021

Explainable and Interpretable Face Presentation Attack Detection Methods

Author
Murilo Leite Nóbrega

Institution
UP-FEUP

2020

Fingerprint Anti Spoofing – Domain Adaptation and Adversarial Learning

Author
João Afonso Pinto Pereira

Institution
UP-FEUP

2020

Explainable Artificial Intelligence For Biometric Analysis

Author
Pedro Carneiro Neto

Institution
UP-FEUP

2020

Head Pose Estimation for Biometric Recognition Systems

Author
João Manuel Guedes Ferreira

Institution
UP-FEUP

2020

Face biOmetrics UNder severe representation Drifts

Author
Mohsen Saffari

Institution
UP-FEUP