Publications

Despite prejudice cannot be directly observed, nonverbal behaviours provide profound hints on people inclinations. In this paper, we use recent sensing technologies and machine learning techniques to automatically infer the results of psychological questionnaires frequently used to assess implicit prejudice. In particular, we recorded 32 students discussing with both white and black collaborators. Then, we identified a set of features allowing automatic extraction and measured their degree of correlation with psychological scores. Results confirmed that automated analysis of nonverbal behaviour is actually possible thus paving the way for innovative clinical tools and eventually more secure societies.

Facial expression and gesture recognition algorithms are key enabling technologies for human-computer interaction (HCI) systems. State of the art approaches for automatic detection of body movements and analyzing emotions from facial features heavily rely on advanced machine learning algorithms. Most of these methods are designed for the average user, but the assumption “one-size-fits-all” ignores diversity in cultural background, gender, ethnicity, and personal behavior, and limits their applicability in real-world scenarios. A possible solution is to build personalized interfaces, which practically implies learning person-specific classifiers and usually collecting a significant amount of labeled samples for each novel user. As data annotation is a tedious and time-consuming process, in this paper we present a framework for personalizing classification models which does not require labeled target data. Personalization is achieved by devising a novel transfer learning approach. Specifically, we propose a regression framework which exploits auxiliary (source) annotated data to learn the relation between person-specific sample distributions and parameters of the corresponding classifiers. Then, when considering a new target user, the classification model is computed by simply feeding the associated (unlabeled) sample distribution into the learned regression function. We evaluate the proposed approach in different applications: pain recognition and action unit detection using visual data and gestures classification using inertial measurements, demonstrating the generality of our method with respect to different input data types and basic classifiers. We also show the advantages of our approach in terms of accuracy and computational time both with respect to user-independent approaches and to previous personalization techniques.

This paper presents a complete system for shot and scene detection in broadcast videos, as well as a method to select the best representative key-frames, which could be used in new interactive interfaces for accessing large collections of edited videos. The final goal is to enable an improved access to video footage and the re-use of video content with the direct management of user-selected video-clips.

The pervasive availability of the Internet, coupled with the development of increasingly powerful technologies, has led digital images to be the primary source of visual information in nowadays society. However, their reliability as a true representation of reality cannot be taken for granted, due to the affordable powerful graphics editing softwares that can easily alter the original content, leaving no visual trace of any modification on the image making them potentially dangerous. This motivates developing technological solutions able to detect media manipulations without a prior knowledge or extra information regarding the given image. At the same time, the huge amount of available data has also led to tremendous advances of data-hungry learning models, which have already demonstrated in last few years to be successful in image classification. In this work we propose a deep learning approach for tampered image classification. To our best knowledge, this the first attempt to use the deep learning paradigm in an image forensic scenario. In particular, we propose a new blind deep learning approach based on Convolutional Neural Networks (CNN) able to learn invisible discriminative artifacts from manipulated images that can be exploited to automatically discriminate between forged and authentic images. The proposed approach not only detects forged images but it can be extended to localize the tampered regions within the image. This method outperforms the state-of-the-art in terms of accuracy on CASIA TIDE v2.0 dataset. The capability of automatically crafting discriminant features can lead to surprising results. For instance, detecting image compression filters used to create the dataset. This argument is also discussed within this paper.

With the spread of wearable and mobile devices, the request for interactive augmented reality applications is in constant growth. Among the different possibilities, we focus on the cultural heritage domain where a key step in the development applications for augmented cultural experiences is to obtain a precise localization of the user, i.e. the 6 degree-of-freedom of the camera acquiring the images used by the application. Current state of the art perform this task by extracting local descriptors from a query and exhaustively matching them to a sparse 3D model of the environment. While this procedure obtains good localization performance, due to the vast search space involved in the retrieval of 2D-3D correspondences this is often not feasible in real-time and interactive environments. In this paper we hence propose to perform descriptor quantization to reduce the search space and employ multiple KD-Trees combined with a principal component analysis dimensionality reduction to enable an efficient search. We experimentally show that our solution can halve the computational requirements of the correspondence search with regard to the state of the art while maintaining similar accuracy levels.

In this paper we present a method for in vivo surface reconstruction and 3D vessels segmentation from Speckle-Variance Optical Coherence Tomography imaging, applied to dermatology. This novel technology allows to capture motion underneath the skin surface revealing the presence of blood vessels. Standard OCT visualization techniques are inappropriate for this new source of information, that is crucial in early skin cancer diagnosis. We investigate 3D reconstruction techniques for better visualization of both the external and internal structure of skin lesions, as a tool to help clinicians in the task of qualitative tumor evaluation.

Background and objectives. The automated analysis of Indirect Immunofluorescence images for Anti-Nuclear Autoantibody (ANA) testing is a fairly recent field that is receiving ever-growing interest from the research community. ANA testing leverages on the categorization of intensity level and fluorescent pattern of IIF images of HEp-2 cells to perform a differential diagnosis of important autoimmune diseases. Nevertheless, it suffers from tremendous lack of repeatability due to subjectivity in the visual interpretation of the images. The automatization of the analysis is seen as the only valid solution to this problem. Several works in literature address individual steps of the work-flow, nonetheless integrating such steps and assessing their effectiveness as a whole is still an open challenge. Methods. We present a modular tool, ANAlyte, able to characterize a IIF image in terms of fluorescent intensity level and fluorescent pattern without any user-interactions. For this purpose, ANAlyte integrates the following: (i) Intensity Classifier module, that categorizes the intensity level of the input slide based on multi-scale contrast assessment (ii) Cell Segmenter module, that splits the input slide into individual HEp-2 cells; (iii) Pattern Classifier module, that determines the fluorescent pattern of the slide based on the pattern of the individual cells. Results. To demonstrate the accuracy and robustness of our tool, we experimentally validated ANAlyte on two different public benchmarks of IIF HEp-2 images with rigorous leave-one-out cross-validation strategy. We obtained overall accuracy of fluorescent intensity and pattern classification respectively around 85% and above 90%. We assessed all results by comparisons with some of the most representative state of the art works. Conclusions. Unlike most of the other works in the recent literature, ANAlyte aims at the automatization of all the major steps of ANA image analysis. Results on public benchmarks demonstrate that the tool can characterize HEp-2 slides in terms of intensity and fluorescent pattern with accuracy better or comparable with the state of the art techniques, even when such techniques are run on manually segmented cells. Hence, ANAlyte can be proposed as a valid solution to the problem of ANA testing automatization.