Breast cancer is the most prevalent type of cancer among the female world population. Its early detection has a crucial role in enhancing the effectiveness of treatments, as well as reducing serious complications and deaths. Ultrasound imaging represents a standard diagnostic technique for this purpose, due to its low invasiveness and cost. However, as this technique is susceptible to a certain degree of uncertainty, computer-aided solutions have been proposed in recent years to reduce the operator workload and improve the accuracy of diagnoses. Following this trend, the present study aims to design and propose a fully-automated and multi-layer pipeline for the segmentation and classification of breast lesions associated with cancer risk, from ultrasound images. To achieve this goal, we first evaluate and compare the performance of several Convolutional Neural Network (CNN) architectures in tackling the above tasks. Then, we combine the performance of such networks through specialized ensembles, to better discriminate among heterogeneous cases. Lastly, we present a novel step of cyclic mutual optimization that exploits the intermediate results of the classification step to improve the segmentation outcome and vice versa, in an iterative manner. Experimental findings obtained on public datasets show the superiority of the ensemble methods over the individual networks. Moreover, with a Dice coefficient of 82% in the segmentation task and an accuracy of 91% in the classification task, our best configuration also shows to be competitive with respect to the state-of-the-art.

In the last decade, market financial forecasting has attracted high interests amongst the researchers in pattern recognition. Usually, the data used for analysing the market, and then gamble on its future trend, are provided as time series; this aspect, along with the high fluctuation of this kind of data, cuts out the use of very efficient classification tools, very popular in the state of the art, like the well known convolutional neural networks ( CNNs ) models such as Inception, ResNet, AlexNet, and so on. This forces the researchers to train new tools from scratch. Such operations could be very time consuming. This paper exploits an ensemble of CNNs, trained over Gramian angular fields ( GAF ) images, generated from time series related to the Standard - Poor’s 500 index future; the aim is the prediction of the future trend of the U.S. market. A multi-resolution imaging approach is used to feed each CNN, enabling the analysis of different time intervals for a single observation. A simple trading system based on the ensemble forecaster is used to evaluate the quality of the proposed approach. Our method outperforms the buy-And-hold ( B - H ) strategy in a time frame where the latter provides excellent returns. Both quantitative and qualitative results are provided.

Interest in the security of individuals has increased in recent years. This increase has in turn led to much wider deployment of surveillance cameras worldwide, and consequently, automated surveillance systems research has received more attention from the scientific community than before. Concurrently, biometrics research has become more popular as well, and it is supported by the increasing number of approaches devised to address specific degradation factors of unconstrained environments. Despite these recent efforts, no automated surveillance system that performs reliable biometric recognition in such an environment has become available. Nevertheless, recent developments in human motion analysis and biometric recognition suggest that both can be combined to develop a fully automated system. As such, this paper reviews recent advances in both areas, with a special focus on surveillance scenarios. When compared to previous studies, we highlight two distinct features, i.e., (1) our emphasis is on approaches that are devised to work in unconstrained environments and surveillance scenarios; and (2) biometric recognition is the final goal of the surveillance system, as opposed to behavior analysis, anomaly detection or action recognition.

Soft biometrics have been emerging to complement other traits and are particularly useful for poor quality data. In this paper, we propose an efficient algorithm to estimate human head poses and to infer soft biometric labels based on the 3D morphology of the human head. Starting by considering a set of pose hypotheses, we use a learning set of head shapes synthesized from anthropometric surveys to derive a set of 3D head centroids that constitutes a metric space. Next, representing queries by sets of 2D head landmarks, we use projective geometry techniques to rank efficiently the joint 3D head centroids/pose hypotheses according to their likelihood of matching each query. The rationale is that the most likely hypotheses are sufficiently close to the query, so a good solution can be found by convex energy minimization techniques. Once a solution has been found, the 3D head centroid and the query are assumed to have similar morphology, yielding the soft label. Our experiments point toward the usefulness of the proposed solution, which can improve the effectiveness of face recognizers and can also be used as a privacy-preserving solution for biometric recognition in public environments.