Search

The article discusses three Argentine laboratories that conduct research & development (R&D) activities in image sciences. It profiles the Imaging Sciences Laboratory of the Universidad Nacional del Sur, the PLADEMA Institute at the Universidad Nacional del Centro de la Provincia de Buenos Aires, and the Image Processing Laboratory at the Universidad Nacional de Mar del Plata.

Ergonomic risk assessment is now, due to an increased awareness, carried out more often than in the past. The conventional risk assessment evaluation, based on expert-assisted observation of the workplaces and manually filling in score tables, is still predominant. Data analysis is usually done with a focus on critical moments, although without the support of contextual information and changes over time. In this paper we introduce ErgoExplorer, a system for the interactive visual analysis of risk assessment data. In contrast to the current practice, we focus on data that span across multiple actions and multiple workers while keeping all contextual information. Data is automatically extracted from video streams. Based on carefully investigated analysis tasks, we introduce new views and their corresponding interactions. These views also incorporate domain-specific score tables to guarantee an easy adoption by domain experts. All views are integrated into ErgoExplorer, which relies on coordinated multiple views to facilitate analysis through interaction. ErgoExplorer makes it possible for the first time to examine complex relationships between risk assessments of individual body parts over long sessions that span multiple operations. The newly introduced approach supports analysis and exploration at several levels of detail, ranging from a general overview, down to inspecting individual frames in the video stream, if necessary. We illustrate the usefulness of the newly proposed approach applying it to several datasets.

A flexible and cheap model to measure refraction through generic objects is presented. The approach is founded on the theoretical optical path of a light ray through a generic object. Translucid objects are estimated as spherical lenses and the optical expressions were obtained. The model may need complex shape approximations as a string of lenses since the model results in insufficient approximations of complicated objects.

AbstractThe Developmental Origins of Health and Disease (DOHaD) framework aims to understand how environmental exposures in early life shape lifecycle health. Our understanding and the ability to prevent poor health outcomes and enrich for resiliency remain limited, in part, because exposure–outcome relationships are complex and poorly defined. We, therefore, aimed to determine the major DOHaD risk and resilience factors. A systematic approach with a 3-level screening process was used to conduct our Rapid Evidence Review following the established guidelines. Scientific databases using DOHaD-related keywords were searched to capture articles between January 1, 2009 and April 19, 2019. A final total of 56 systematic reviews/meta-analyses were obtained. Studies were categorized into domains based on primary exposures and outcomes investigated. Primary summary statistics and extracted data from the studies are presented in Graphical Overview for Evidence Reviews diagrams. There was substantial heterogeneity within and between studies. While global trends showed an increase in DOHaD publications over the last decade, the majority of data reported were from high-income countries. Articles were categorized under six exposure domains: Early Life Nutrition, Maternal/Paternal Health, Maternal/Paternal Psychological Exposure, Toxicants/Environment, Social Determinants, and Others. Studies examining social determinants of health and paternal influences were underrepresented. Only 23% of the articles explored resiliency factors. We synthesized major evidence on relationships between early life exposures and developmental and health outcomes, identifying risk and resiliency factors that influence later life health. Our findings provide insight into important trends and gaps in knowledge within many exposures and outcome domains.

The authors propose a video-summarisation method based on visual and categorical diversities using pre-trained deep visual and categorical models. Their method extracts visual and categorical features from a pre-trained deep convolutional network (DCN) and a pre-trained word-embedding matrix. Using visual and categorical information they obtain a video diversity estimation, which is used as an importance score to select segments from the input video that best describes it. Their method also allows performing queries during the search process, in this way personalising the resulting video summaries according to the particular intended purposes. The performance of the method is evaluated using different pre-trained DCN models in order to select the architecture with the best throughput. They then compare it with other state-of-the-art proposals in video summarisation using a data-driven approach with the public dataset SumMe, which contains annotated videos with per-fragment importance. The results show that their method outperforms other proposals in most of the examples. As an additional advantage, their method requires a simple and direct implementation that does not require a training stage.

Accurate gathering of phenotypic information is a key aspect in several subject matters, including biometrics, biomedical analysis, forensics, and many other. Automatic identification of anatomical structures of biometric interest, such as fingerprints, iris patterns, or facial traits, are extensively used in applications like access control and anthropological research, all having in common the drawback of requiring intrusive means for acquiring the required information. In this regard, the ear structure has multiple advantages. Not only the ear's biometric markers can be easily captured from the distance with non intrusive methods, but also they experiment almost no changes over time, and are not influenced by facial expressions. Here we present a new method based on Geometric Morphometrics and Deep Learning for automatic ear detection and feature extraction in the form of landmarks. A convolutional neural network was trained with a set of manually landmarked examples. The network is able to provide morphometric landmarks on ears' images automatically, with a performance that matches human landmarking. The feasibility of using ear landmarks as feature vectors opens a novel spectrum of biometrics applications.

Form and shape descriptors are among the most useful features for object identification and recognition. Even though there exists a widely used set of shape descriptors and underlying computational methods for their evaluation, frequently they fail to distinguish among very similar objects that they appear very different to the human eye. The authors propose a new set of shape descriptors based on a finer determination of the object symmetry axes, and a more accurate estimation of the bilateral and radial symmetries. These descriptors were thoroughly tested using several synthetic and real objects with varying degrees of symmetry. The methods for axes estimation and symmetry descriptors extraction outperform the widespread shape descriptors in recognising and identifying among very similar objects.

Descriptors extracted from magnetic resonance imaging (MRI) of the brain can be employed to locate and characterize a wide range of pathologies. Scalar measures are typically derived within a single-voxel unit, but neighborhood-based texture measures can also be applied. In this work, we propose a new set of descriptors to compute local texture characteristics from scalar measures of diffusion tensor imaging (DTI), such as mean and radial diffusivity, and fractional anisotropy. We employ weighted rotational invariant local operators, namely standard deviation, inter-quartile range, coefficient of variation, quartile coefficient of variation and skewness. Sensitivity and specificity of those texture descriptors were analyzed with tract-based spatial statistics of the white matter on a diffusion MRI group study of elderly healthy controls, patients with mild cognitive impairment (MCI), and mild or moderate Alzheimer’s disease (AD). In addition, robustness against noise has been assessed with a realistic diffusion-weighted imaging phantom and the contamination of the local neighborhood with gray matter has been measured. The new texture operators showed an increased ability for finding formerly undetected differences between groups compared to conventional DTI methods. In particular, the coefficient of variation, quartile coefficient of variation, standard deviation and inter-quartile range of the mean and radial diffusivity detected significant differences even between previously not significantly discernible groups, such as MCI versus moderate AD and mild versus moderate AD. The analysis provided evidence of low contamination of the local neighborhood with gray matter and high robustness against noise. The local operators applied here enhance the identification and localization of areas of the brain where cognitive impairment takes place and thus indicate them as promising extensions in diffusion MRI group studies.

Digital video has become a very popular media in several contexts, with an ever expanding horizon of applications and uses. Thus, the amount of available video information is growing almost limitless. For this reason, video summarization continues to attract the attention of a wide spectrum of research efforts. In this work, the authors present a novel video summarization technique based on tracking local features among consecutive frames. The authors' approach operates on the uncompressed domain, and requires only a small set of consecutive frames to perform. Additionally, the authors' algorithm processes the video stream directly and produces results on the fly. The authors tested their implementation with standard available datasets, and compared the results with the most recently published work in the field. The achieved results are similar or better in quality than the best performing proposals, with the additional advantage of being able to process the stream directly in the uncompressed domain.