Search

Presentation attack detection is a challenging problem that aims at exposing an impostor user seeking to deceive the authentication system. In facial biometrics systems, this kind of attack is performed using a photograph, video, or 3D mask containing the biometric information of a genuine identity. In this paper, we propose a novel approach to detecting face presentation attacks based on intrinsic properties of the scene such as albedo, depth, and reflectance properties of the facial surfaces, which were recovered through a shape-from-shading (SfS) algorithm. To extract meaningful patterns from the different maps obtained with the SfS algorithm, we designed a novel shallow CNN architecture for learning features useful to the presentation attack detection (PAD). We performed several experiments considering the intra- and inter-dataset evaluation protocols. The obtained results showed the effectiveness of the proposed method considering several types of photo- and video-based presentation attacks, and in the cross-sensor scenario, besides achieving competitive results for the inter-dataset evaluation protocol.

The very idea of hiring humans to avoid the indiscriminate spread of inappropriate sensitive content online (e.g., child pornography and violence) is daunting. The inherent data deluge and the tediousness of the task call for more adequate approaches, and set the stage for computer-aided methods. If running in the background, such methods could readily cut the stream flow at the very moment of inadequate content exhibition, being invaluable for protecting unwary spectators. Except for the particular case of violence detection, related work to sensitive video analysis has mostly focused on deciding whether or not a given stream is sensitive, leaving the localization task largely untapped. Identifying when a stream starts and ceases to display inappropriate content is key for live streams and video on demand. In this work, we propose a novel multimodal fusion approach to sensitive scene localization. The solution can be applied to diverse types of sensitive content, without the need for step modifications (general purpose). We leverage the multimodality data nature of videos (e.g., still frames, video space-time, audio stream, etc.) to effectively single out frames of interest. To validate the solution, we perform localization experiments on pornographic and violent video streams, two of the commonest types of sensitive content, and report quantitative and qualitative results. The results show, for instance, that the proposed method only misses about five minutes in every hour of streamed pornographic content. Finally, for the particular task of pornography localization, we also introduce the first frame-level annotated pornographic video dataset to date, which comprises 140 h of video, freely available for downloading.

Energy and storage restrictions are relevant variables that software applications should be concerned about when running in low-power environments. In particular, computer vision (CV) applications exemplify well that concern, since conventional uniform image sensors typically capture large amounts of data to be further handled by the appropriate CV algorithms. Moreover, much of the acquired data are often redundant and outside of the application’s interest, which leads to unnecessary processing and energy spending. In the literature, techniques for sensing and re-sampling images in non-uniform fashions have emerged to cope with these problems. In this study, we propose Application-Oriented Retinal Image Models that define a space-variant configuration of uniform images and contemplate requirements of energy consumption and storage footprints for CV applications. We hypothesize that our models might decrease energy consumption in CV tasks. Moreover, we show how to create the models and validate their use in a face detection/recognition application, evidencing the compromise between storage, energy, and accuracy. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

We propose a new method to improve median plane sound localization performance using a nonlinear representation of head-related transfer functions (HRTFs) and a recommender system. First, we reduce the dimensionality of an HRTF data set with multiple subjects using manifold learning in conjunction with a customized intersubject graph which takes into account relevant prior knowledge of HRTFs. Then, we use a sound localization model to estimate a subject's localization performance in terms of polar error and quadrant error rate. These metrics are merged to form a single rating per HRTF pair that we feed into a recommender system. Finally, the recommender system takes the low-dimensional HRTF representation as well as the ratings obtained from the localization model to predict the best HRTF set, possibly constructed by mixing HRTFs from different individuals, that minimizes a subject's localization error. The simulation results show that our method is capable of choosing a set of HRTFs that improves the median plane localization performance with respect to the mean localization performance using non-individualized HRTFs. Moreover, the localization performance achieved by our HRTF recommender system shows no significant difference to the localization performance observed with the best matching non-individualized HRTFs but with the advantage of not having to perform listening tests with all individuals' HRTFs from the database.

Mobile devices are becoming ubiquitous and, sometimes, even extensions of ourselves. These devices are growing fast in terms of delivered computational power, storage capacity, battery duration, and built-in sensors. Time and again, we see headlines advertising new unforeseen applications leveraging this power, especially the sensors, for solving diverse problems, including fall detection, user’s activity recognition, location identification, or even user authentication based on the way of walking (gait). In this paper, we focus on motion sensors and discuss how the provided data can be interpreted and transformed to better serve different purposes. We propose a method to process the data from such sensors that reduces the acquisition noise and possible artifacts, and turns the data invariant to the device’s position and the user’s movement direction. We introduce a new coordinate system referred to as user-centric, as opposed to the two most common coordinate systems used—the device and world-coordinate systems. For testing, we design and develop a user recognition system based on gait, in which the three coordinates systems are compared and discussed considering a one-versus-rest authentication setup. The results show the importance of properly pre-processing the acquired data to enable more reliable applications underpinned by mobile sensors.

Image phylogeny is the problem of reconstructing the structure that represents the history of generation of semantically similar images (e.g., near-duplicate images). Typical image phylogeny approaches break the problem into two steps: (1) estimating the dissimilarity between each pair of images and (2) reconstructing the phylogeny structure. Given that the dissimilarity calculation directly impacts the phylogeny reconstruction, in this paper, we propose new approaches to the standard formulation of the dissimilarity measure employed in image phylogeny, aiming at improving the reconstruction of the tree structure that represents the generational relationships between semantically similar images. These new formulations exploit a different method of color adjustment, local gradients to estimate pixel differences and mutual information as a similarity measure. The results obtained with the proposed formulation remarkably outperform the existing counterparts in the literature, allowing a much better analysis of the kinship relationships in a set of images, allowing for more accurate deployment of phylogeny solutions to tackle traitor tracing, copyright enforcement and digital forensics problems.

Recent literature has explored automated pornographic detection - a bold move to replace humans in the tedious task of moderating online content. Unfortunately, on scenes with high skin exposure, such as people sunbathing and wrestling, the state of the art can have many false alarms. This paper is based on the premise that incorporating motion information in the models can alleviate the problem of mapping skin exposure to pornographic content, and advances the bar on automated pornography detection with the use of motion information and deep learning architectures. Deep Learning, especially in the form of Convolutional Neural Networks, have striking results on computer vision, but their potential for pornography detection is yet to be fully explored through the use of motion information. We propose novel ways for combining static (picture) and dynamic (motion) information using optical flow and MPEG motion vectors. We show that both methods provide equivalent accuracies, but that MPEG motion vectors allow a more efficient implementation. The best proposed method yields a classification accuracy of 97.9% - an error reduction of 64.4% when compared to the state of the art - on a dataset of 800 challenging test cases. Finally, we present and discuss results on a larger, and more challenging, dataset.

We propose a new head-related transfer function (HRTF) interpolation method using Isomap, a nonlinear dimensionality reduction technique. First, we construct a single manifold for all subjects across both azimuth and elevation angles through the construction of an intersubject graph (ISG) that includes important prior knowledge of the HRTFs such as correlations across individuals, directions, and ears. Then, for a new direction, we predict its corresponding low-dimensional HRTF by interpolating over same subject low-dimensional measured HRTFs. Finally, we use a local neighborhood mapping in the manifold to reconstruct the high-dimensional HRTF from measured HRTFs of all subjects. We show that a single manifold representation obtained through the ISG is a powerful way to allow measured HRTFs from different subjects to contribute for reconstructing the HRTFs for new directions. Moreover, our results suggest that a small number of spatial measurements capture most of acoustical properties of HRTFs. Finally, our approach outperforms other linear and nonlinear dimensionality reduction techniques such as principal component analysis, locally linear embedding, and Laplacian eigenmaps.