Cookies Policy
We use cookies to improve our site and your experience. By continuing to browse our site you accept our cookie policy. Find out More
Close
  • Menu
About
Download Photo HD

About

Ana Rebelo is involved in research and development activities as a senior researcher at the Visual Computing and Machine Intelligence (VCMI) Group in the Centre for Telecommunications and Multimedia (CTM) of INESC TEC. Simultaneously, she is an Assistant Professor at Universidade Portucalense where she is the Coordinator of Master's Degree in Data Science that has a study plan that covers the hot topics of machine learning, computer vision, big data and natural language processing. At INESC TEC Rebelo has been developing and implementing Computer Vision and Machine Learning algorithms for biometric and forensic applications. She is responsible for seeking funded research projects, scientific advisory and project coordination in several R&D projects, having collaborations with several companies and other research centers. She is the co-founder and co-leader of the VISion Understanding and Machine intelligence Summer School a non-profit summer school that aims to gather Ph.D. candidates, Post-Doctoral scholars and researchers from academia and industry with research interests in computer vision and machine intelligence. Ana Rebelo holds a PhD in Electrical and Computer Engineering from the University of Porto-Portugal.

Interest
Topics
Details

Details

003
Publications

2019

On the role of multimodal learning in the recognition of sign language

Authors
Ferreira, PM; Cardoso, JS; Rebelo, A;

Publication
Multimedia Tools and Applications

Abstract
Sign Language Recognition (SLR) has become one of the most important research areas in the field of human computer interaction. SLR systems are meant to automatically translate sign language into text or speech, in order to reduce the communicational gap between deaf and hearing people. The aim of this paper is to exploit multimodal learning techniques for an accurate SLR, making use of data provided by Kinect and Leap Motion. In this regard, single-modality approaches as well as different multimodal methods, mainly based on convolutional neural networks, are proposed. Our main contribution is a novel multimodal end-to-end neural network that explicitly models private feature representations that are specific to each modality and shared feature representations that are similar between modalities. By imposing such regularization in the learning process, the underlying idea is to increase the discriminative ability of the learned features and, hence, improve the generalization capability of the model. Experimental results demonstrate that multimodal learning yields an overall improvement in the sign recognition performance. In particular, the novel neural network architecture outperforms the current state-of-the-art methods for the SLR task. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.

2019

DeSIRe: Deep Signer-Invariant Representations for Sign Language Recognition

Authors
Ferreira, PM; Pernes, D; Rebelo, A; Cardoso, JS;

Publication
IEEE Transactions on Systems, Man, and Cybernetics: Systems

Abstract

2018

Physiological Inspired Deep Neural Networks for Emotion Recognition

Authors
Ferreira, PM; Marques, F; Cardoso, JS; Rebelo, A;

Publication
IEEE ACCESS

Abstract
Facial expression recognition (FER) is currently one of the most active research topics due to its wide range of applications in the human-computer interaction field. An important part of the recent success of automatic FER was achieved thanks to the emergence of deep learning approaches. However, training deep networks for FER is still a very challenging task, since most of the available FER data sets are relatively small. Although transfer learning can partially alleviate the issue, the performance of deep models is still below of its full potential as deep features may contain redundant information from the pre-trained domain. Instead, we propose a novel end-to-end neural network architecture along with a well-designed loss function based on the strong prior knowledge that facial expressions are the result of the motions of some facial muscles and components. The loss function is defined to regularize the entire learning process so that the proposed neural network is able to explicitly learn expression-specific features. Experimental results demonstrate the effectiveness of the proposed model in both lab-controlled and wild environments. In particular, the proposed neural network provides quite promising results, outperforming in most cases the current state-of-the-art methods.

2018

Are Deep Learning Methods Ready for Prime Time in Fingerprints Minutiae Extraction?

Authors
Rebelo, A; Oliveira, T; Correia, ME; Cardoso, JS;

Publication
Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications - Lecture Notes in Computer Science

Abstract

2018

Robust Clustering-based Segmentation Methods for Fingerprint Recognition

Authors
Ferreira, PM; Sequeira, AF; Cardoso, JS; Rebelo, A;

Publication
2018 International Conference of the Biometrics Special Interest Group, BIOSIG 2018

Abstract
Fingerprint recognition has been widely studied for more than 45 years and yet it remains an intriguing pattern recognition problem. This paper focuses on the foreground mask estimation which is crucial for the accuracy of a fingerprint recognition system. The method consists of a robust cluster-based fingerprint segmentation framework incorporating an additional step to deal with pixels that were rejected as foreground in a decision considered not reliable enough. These rejected pixels are then further analysed for a more accurate classification. The procedure falls in the paradigm of classification with reject option- a viable option in several real world applications of machine learning and pattern recognition, where the cost of misclassifying observations is high. The present work expands a previous method based on the fuzzy C-means clustering with two variations regarding: i) the filters used; and ii) the clustering method for pixel classification as foreground/background. Experimental results demonstrate improved results on FVC datasets comparing with state-of-the-art methods even including methodologies based on deep learning architectures. © 2018 Gesellschaft fuer Informatik.

Supervised
thesis

2015

Smart Image Retargeting Techniques

Author
Laura Figueiredo Ângelo

Institution
UP-FEUP

2015

Portuguese Sign Language recognition

Author
Pedro Miguel Martins Ferreira

Institution
UP-FEUP