2015
Authors
Mendonça, T; Ferreira, P; Marçal, A; Barata, C; Marques, J; Rocha, J; Rozeira, J;
Publication
Dermoscopy Image Analysis - Digital Imaging and Computer Vision
Abstract
2018
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
Authors
Ferreira, PM; Sequeira, AF; Cardoso, JS; Rebelo, A;
Publication
2018 INTERNATIONAL CONFERENCE OF THE BIOMETRICS SPECIAL INTEREST GROUP (BIOSIG)
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.
2012
Authors
Ferreira, PM; Mendonça, T; Rozeira, J; Rocha, P;
Publication
Proceedings of the 1st International Workshop on Visual Interfaces for Ground Truth Collection in Computer Vision Applications, VIGTA@AVI 2012, Capri, Italy, May 21, 2012
Abstract
Dermoscopy is a non-invasive diagnostic technique for the in vivo observation of pigmented skin lesions, and it is currently one of the most important imaging techniques for melanoma diagnosis. Since the diagnostic accuracy of dermoscopy significantly depends on the experience of the dermatologists, and the visual interpretation and examination of this kind of images is time consuming, several computer-aided diagnosis systems of digital dermoscopic images have been introduced. However, a reliable ground truth database of manually segmented images is necessary for the development and validation of automatic segmentation and classification methods. As the ground truth database have to be created by expert dermatologists, there is a need for the development of annotation tools that can support the manual segmentation of dermoscopic images, and this way make this task easier and practicable for dermatologists. In this paper we present an annotation tool for manual segmentation of dermoscopic images. This tool allows building up a ground truth database with the manual segmentations both of pigmented skin lesions and of other regions of interest, whose recognition is essential for the development of computer-aided diagnosis systems. © 2012 ACM.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.