Explore the vast range of titles available.

The automatic detection of eye positions, their temporal consistency, and their mapping into a line of sight in the real world (to find where a person is looking at) is reported in the scientific literature as gaze tracking. This has become a very hot topic in the field of computer vision during the last decades, with a surprising and continuously growing number of application fields. A very long journey has been made from the first pioneering works, and this continuous search for more accurate solutions process has been further boosted in the last decade when deep neural networks have revolutionized the whole machine learning area, and gaze tracking as well. In this arena, it is being increasingly useful to find guidance through survey/review articles collecting most relevant works and putting clear pros and cons of existing techniques, also by introducing a precise taxonomy. This kind of manuscripts allows researchers and technicians to choose the better way to move towards their application or scientific goals. In the literature, there exist holistic and specifically technological survey documents (even if not updated), but, unfortunately, there is not an overview discussing how the great advancements in computer vision have impacted gaze tracking. Thus, this work represents an attempt to fill this gap, also introducing a wider point of view that brings to a new taxonomy (extending the consolidated ones) by considering gaze tracking as a more exhaustive task that aims at estimating gaze target from different perspectives: from the eye of the beholder (first-person view), from an external camera framing the beholder’s, from a third-person view looking at the scene where the beholder is placed in, and from an external view independent from the beholder.

Epidemiological figures of the SARS-CoV-2 epidemic in Italy are higher than those observed in China. Our objective was to model the SARS-CoV-2 outbreak progression in Italian regions vs. Lombardy to assess the epidemic’s progression. Our setting was Italy, and especially Lombardy, which is experiencing a heavy burden of SARS-CoV-2 infections. The peak of new daily cases of the epidemic has been reached on the 29th, while was delayed in Central and Southern Italian regions compared to Northern ones. In our models, we estimated the basic reproduction number (R0), which represents the average number of people that can be infected by a person who has already acquired the infection, both by fitting the exponential growth rate of the infection across a 1-month period and also by using day-by-day assessments based on single observations. We used the susceptible–exposed–infected–removed (SEIR) compartment model to predict the spreading of the pandemic in Italy. The two methods provide an agreement of values, although the first method based on exponential fit should provide a better estimation, being computed on the entire time series. Taking into account the growth rate of the infection across a 1-month period, each infected person in Lombardy has involved 4 other people (3.6 based on data of April 23rd) compared to a value of R 0 = 2.68 , as reported in the Chinese city of Wuhan. According to our model, Piedmont, Veneto, Emilia Romagna, Tuscany and Marche will reach an R0 value of up to 3.5. The R0 was 3.11 for Lazio and 3.14 for the Campania region, where the latter showed the highest value among the Southern Italian regions, followed by Apulia (3.11), Sicily (2.99), Abruzzo (3.0), Calabria (2.84), Basilicata (2.66), and Molise (2.6). The R0 value is decreased in Lombardy and the Northern regions, while it is increased in Central and Southern regions. The expected peak of the SEIR model is set at the end of March, at a national level, with Southern Italian regions reaching the peak in the first days of April. Regarding the strengths and limitations of this study, our model is based on assumptions that might not exactly correspond to the evolution of the epidemic. What we know about the SARS-CoV-2 epidemic is based on Chinese data that seems to be different than those from Italy; Lombardy is experiencing an evolution of the epidemic that seems unique inside Italy and Europe, probably due to demographic and environmental factors.

Alzheimer’s disease (AD) is the most common form of dementia. Computer-aided diagnosis (CAD) can help in the early detection of associated cognitive impairment. The aim of this work is to improve the automatic detection of dementia in MRI brain data. For this purpose, we used an established pipeline that includes the registration, slicing, and classification steps. The contribution of this research was to investigate for the first time, to our knowledge, three current and promising deep convolutional models (ResNet, DenseNet, and EfficientNet) and two transformer-based architectures (MAE and DeiT) for mapping input images to clinical diagnosis. To allow a fair comparison, the experiments were performed on two publicly available datasets (ADNI and OASIS) using multiple benchmarks obtained by changing the number of slices per subject extracted from the available 3D voxels. The experiments showed that very deep ResNet and DenseNet models performed better than the shallow ResNet and VGG versions tested in the literature. It was also found that transformer architectures, and DeiT in particular, produced the best classification results and were more robust to the noise added by increasing the number of slices. A significant improvement in accuracy (up to 7%) was achieved compared to the leading state-of-the-art approaches, paving the way for the use of CAD approaches in real-world applications.

Neurodevelopmental disorders (NDD) are impairments of the growth and development of the brain and/or central nervous system. In the light of clinical findings on early diagnosis of NDD and prompted by recent advances in hardware and software technologies, several researchers tried to introduce automatic systems to analyse the baby’s movement, even in cribs. Traditional technologies for automatic baby motion analysis leverage contact sensors. Alternatively, remotely acquired video data (e.g., RGB or depth) can be used, with or without active/passive markers positioned on the body. Markerless approaches are easier to set up and maintain (without any human intervention) and they work well on non-collaborative users, making them the most suitable technologies for clinical applications involving children. On the other hand, they require complex computational strategies for extracting knowledge from data, and then, they strongly depend on advances in computer vision and machine learning, which are among the most expanding areas of research. As a consequence, also markerless video-based analysis of movements in children for NDD has been rapidly expanding but, to the best of our knowledge, there is not yet a survey paper providing a broad overview of how recent scientific developments impacted it. This paper tries to fill this gap and it lists specifically designed data acquisition tools and publicly available datasets as well. Besides, it gives a glimpse of the most promising techniques in computer vision, machine learning and pattern recognition which could be profitably exploited for children motion analysis in videos.

Digital holography (DH) has emerged as one of the most effective coherent imaging technologies. The technological developments of digital sensors and optical elements have made DH the primary approach in several research fields, from quantitative phase imaging to optical metrology and 3D display technologies, to name a few. Like many other digital imaging techniques, DH must cope with the issue of speckle artifacts, due to the coherent nature of the required light sources. Despite the complexity of the recently proposed de-speckling methods, many have not yet attained the required level of effectiveness. That is, a universal denoising strategy for completely suppressing holographic noise has not yet been established. Thus the removal of speckle noise from holographic images represents a bottleneck for the entire optics and photonics scientific community. This review article provides a broad discussion about the noise issue in DH, with the aim of covering the best-performing noise reduction approaches that have been proposed so far. Quantitative comparisons among these approaches will be presented.

The recognition of COVID-19 infection from X-ray images is an emerging field in the learning and computer vision community. Despite the great efforts that have been made in this field since the appearance of COVID-19 (2019), the field still suffers from two drawbacks. First, the number of available X-ray scans labeled as COVID-19-infected is relatively small. Second, all the works that have been carried out in the field are separate; there are no unified data, classes, and evaluation protocols. In this work, based on public and newly collected data, we propose two X-ray COVID-19 databases, which are three-class COVID-19 and five-class COVID-19 datasets. For both databases, we evaluate different deep learning architectures. Moreover, we propose an Ensemble-CNNs approach which outperforms the deep learning architectures and shows promising results in both databases. In other words, our proposed Ensemble-CNNs achieved a high performance in the recognition of COVID-19 infection, resulting in accuracies of 100% and 98.1% in the three-class and five-class scenarios, respectively. In addition, our approach achieved promising results in the overall recognition accuracy of 75.23% and 81.0% for the three-class and five-class scenarios, respectively. We make our databases of COVID-19 X-ray scans publicly available to encourage other researchers to use it as a benchmark for their studies and comparisons.

The aging global population requires innovative remote monitoring systems to assist doctors and caregivers in assessing the health of elderly patients. Doctors often lack access to continuous behavioral data, making it difficult to detect deviations from normal patterns when elderly patients arrive for a consultation. Without historical insights into common behaviors and potential anomalies detected with unobtrusive techniques (e.g., non-wearable devices), timely and informed medical interventions become challenging. To address this, we propose an edge-based Internet of Things (IoT) framework that enables real-time monitoring and anomaly detection using non-wearable sensors to assist doctors and caregivers in assessing the health of elderly patients. By processing data locally, the system minimizes privacy concerns and ensures immediate data availability, allowing healthcare professionals to detect unusual behavioral patterns early. The system employs advanced machine learning (ML) models to identify deviations that may indicate potential health risks. A prototype of our system has been developed to test its feasibility and demonstrate, through the application of two of the most frequently used ML models, i.e., isolation forest and Long Short-Term Memory (LSTM) networks, that it can provide scalability, efficiency, and reliability in the context of elderly care. Further, the provided dashboard enables caregivers and healthcare professionals to access real-time alerts and longitudinal trends, facilitating proactive interventions. The proposed approach improves healthcare responsiveness by providing instant insights into patient behavior, facilitating more accurate diagnoses and interventions. This study lays the groundwork for future advancements in the field and offers valuable insights for the research community to harness the full potential of combining edge computing, artificial intelligence (AI), and the IoT in elderly care.

Since the appearance of the COVID-19 pandemic (at the end of 2019, Wuhan, China), the recognition of COVID-19 with medical imaging has become an active research topic for the machine learning and computer vision community. This paper is based on the results obtained from the 2021 COVID-19 SPGC challenge, which aims to classify volumetric CT scans into normal, COVID-19, or community-acquired pneumonia (Cap) classes. To this end, we proposed a deep-learning-based approach (CNR-IEMN) that consists of two main stages. In the first stage, we trained four deep learning architectures with a multi-tasks strategy for slice-level classification. In the second stage, we used the previously trained models with an XG-boost classifier to classify the whole CT scan into normal, COVID-19, or Cap classes. Our approach achieved a good result on the validation set, with an overall accuracy of 87.75% and 96.36%, 52.63%, and 95.83% sensitivities for COVID-19, Cap, and normal, respectively. On the other hand, our approach achieved fifth place on the three test datasets of SPGC in the COVID-19 challenge, where our approach achieved the best result for COVID-19 sensitivity. In addition, our approach achieved second place on two of the three testing sets.

Developing computer-aided approaches for cancer diagnosis and grading is currently receiving an increasing demand: this could take over intra- and inter-observer inconsistency, speed up the screening process, increase early diagnosis, and improve the accuracy and consistency of the treatment-planning processes.The third most common cancer worldwide and the second most common in women is colorectal cancer (CRC). Grading CRC is a key task in planning appropriate treatments and estimating the response to them. Unfortunately, it has not yet been fully demonstrated how the most advanced models and methodologies of machine learning can impact this crucial task.This paper systematically investigates the use of advanced deep models (convolutional neural networks and transformer architectures) to improve colon carcinoma detection and grading from histological images. To the best of our knowledge, this is the first attempt at using transformer architectures and ensemble strategies for exploiting deep learning paradigms for automatic colon cancer diagnosis. Results on the largest publicly available dataset demonstrated a substantial improvement with respect to the leading state-of-the-art methods. In particular, by exploiting a transformer architecture, it was possible to observe a 3% increase in accuracy in the detection task (two-class problem) and up to a 4% improvement in the grading task (three-class problem) by also integrating an ensemble strategy.

The automatic detection and tracking of human eyes and, in particular, the precise localization of their centers (pupils), is a widely debated topic in the international scientific community. In fact, the extracted information can be effectively used in a large number of applications ranging from advanced interfaces to biometrics and including also the estimation of the gaze direction, the control of human attention and the early screening of neurological pathologies. Independently of the application domain, the detection and tracking of the eye centers are, currently, performed mainly using invasive devices. Cheaper and more versatile systems have been only recently introduced: they make use of image processing techniques working on periocular patches which can be specifically acquired or preliminarily cropped from facial images. In the latter cases the involved algorithms must work even in cases of non-ideal acquiring conditions (e.g in presence of noise, low spatial resolution, non-uniform lighting conditions, etc.) and without user's awareness (thus with possible variations of the eye in scale, rotation and/or translation). Getting satisfying results in pupils' localization in such a challenging operating conditions is still an open scientific topic in Computer Vision. Actually, the most performing solutions in the literature are, unfortunately, based on supervised machine learning algorithms which require initial sessions to set the working parameters and to train the embedded learning models of the eye: this way, experienced operators have to work on the system each time it is moved from an operational context to another. It follows that the use of unsupervised approaches is more and more desirable but, unfortunately, their performances are not still satisfactory and more investigations are required. To this end, this paper proposes a new unsupervised approach to automatically detect the center of the eye: its algorithmic core is a representation of the eye's shape that is obtained through a differential analysis of image intensities and the subsequent combination with the local variability of the appearance represented by self-similarity coefficients. The experimental evidence of the effectiveness of the method was demonstrated on challenging databases containing facial images. Moreover, its capabilities to accurately detect the centers of the eyes were also favourably compared with those of the leading state-of-the-art methods.