Aparecido Nilceu Marana

Murilo Varges da Silva, Aparecido Nilceu Marana

With the increasing use of social networks and mobile devices, the number of videos posted on the Internet is growing exponentially. Among the inappropriate contents published on the Internet, pornography is one of the most worrying as it can be accessed by teens and children. Two spatiotemporal CNNs, VGG-C3D CNN and ResNet R(2+1)D CNN, were assessed for pornography detection in videos in the present study. Experimental results using the Pornography-800 dataset showed that these spatiotemporal CNNs performed better than some state-of-the-art methods based on bag of visual words and are competitive with other CNN-based approaches, reaching accuracy of 95.1%.

Johnatan S. Oliveira, Gustavo B. Souza, Anderson R. Rocha et al.

Ensuring the security of transactions is currently one of the major challenges that banking systems deal with. The usage of face for biometric authentication of users is attracting large investments from banks worldwide due to its convenience and acceptability by people, especially in cross-domain scenarios, in which facial images from ID documents are compared with digital self-portraits (selfies) for the automated opening of new checking accounts, e.g, or financial transactions authorization. Actually, the comparison of selfies and IDs has also been applied in another wide variety of tasks nowadays, such as automated immigration control. The major difficulty in such process consists in attenuating the differences between the facial images compared given their different domains. In this work, in addition to collecting a large cross-domain face dataset, with 27,002 real facial images of selfies and ID documents (13,501 subjects) captured from the databases of the major public Brazilian bank, we propose a novel architecture for such cross-domain matching problem based on deep features extracted by two well-referenced Convolutional Neural Networks (CNN). Results obtained on the dataset collected, called FaceBank, with accuracy rates higher than 93%, demonstrate the robustness of the proposed approach to the cross-domain face matching problem and its feasible application in real banking security systems.

Gustavo Botelho de Souza, João Paulo Papa, Aparecido Nilceu Marana

Biometrics emerged as a robust solution for security systems. However, given the dissemination of biometric applications, criminals are developing techniques to circumvent them by simulating physical or behavioral traits of legal users (spoofing attacks). Despite face being a promising characteristic due to its universality, acceptability and presence of cameras almost everywhere, face recognition systems are extremely vulnerable to such frauds since they can be easily fooled with common printed facial photographs. State-of-the-art approaches, based on Convolutional Neural Networks (CNNs), present good results in face spoofing detection. However, these methods do not consider the importance of learning deep local features from each facial region, even though it is known from face recognition that each facial region presents different visual aspects, which can also be exploited for face spoofing detection. In this work we propose a novel CNN architecture trained in two steps for such task. Initially, each part of the neural network learns features from a given facial region. Afterwards, the whole model is fine-tuned on the whole facial images. Results show that such pre-training step allows the CNN to learn different local spoofing cues, improving the performance and the convergence speed of the final model, outperforming the state-of-the-art approaches.

Lucas Alexandre Ramos, Aparecido Nilceu Marana

The use of physical and behavioral characteristics for human identification is known as biometrics. Among the many biometrics traits available, the fingerprint is the most widely used. The fingerprint identification is based on the impression patterns, as the pattern of ridges and minutiae, characteristics of first and second levels respectively. The current identification systems use these two levels of fingerprint features due to the low cost of the sensors. However, due the recent advances in sensor technology, it is possible to use third level features present within the ridges, such as the perspiration pores. Recent studies have shown that the use of third-level features can increase security and fraud protection in biometric systems, since they are difficult to reproduce. In addition, recent researches have also focused on multibiometrics recognition due to its many advantages. The goal of this work was to apply fusion techniques for fingerprint recognition in order to combine minutiae, ridges and pore-based methods and, thus, provide more robust biometrics recognition systems. We evaluated isotropic-based and adaptive-based automatic pore extraction methods and the fusion of pore-based method with the identification methods based on minutiae and ridges. The experiments were performed on the public database PolyU HRF and showed a reduction of approximately 16% in the Equal Error Rate compared to the best results obtained by the methods individually.