Search

Restoring artworks seriously damaged or completely destroyed is a challenging task. In particular, the reconstruction of frescoes has to deal with problems such as very small fragments, irregular shapes and missing pieces. Several attempts have been done to develop new techniques for helping restorers in the matching process, starting from traditional image processing methods to the more recent deep learning approaches. However, as often happens in the Cultural Heritage field, the availability of labeled data to test new strategies is limited, and publicly available datasets contain only few samples. For this reason, in this paper we introduce DAFNE, a large dataset that includes hundreds of thousands of images of fresco fragments artificially generated to guarantee a high variability in terms of shapes and dimensions. Fragments have been obtained starting from 62 images of famous frescoes of various artists and historical periods, in order to consider different artistic styles, subjects and colors.

A novel framework for Eurocode 8-compliant design using Linear Time-History Analysis (LTHA) is discussed. LTHA overcomes the approximations typical of other linear seismic analyses but it still lacks a suitable approach for seismic input selection compatible with Eurocode 8-prescriptions. The critical aspect is to find a balanced compromise to control seismic input variability, suiting design purposes, but still being able to capture specific response features such as pulse-like effects. A LTHA design procedure has been included in ASCE/SEI 7-16 (2017) and described in FEMA P-1050 (2015), suggesting spectral-matching of three ground motions as input, so that LTHA can be used as alternative to Response Spectrum Analysis (RSA). Herein, a 12-storey regular Reinforced Concrete Moment Resisting Frame building is employed as case-study. Different ground motion selection strategies are compared. Firstly, three suites of spectrum compatible ground motions are used referring to requirements of Eurocode 8 for nonlinear time-history analysis and compared with LTHA-ground motion selection procedure included in FEMA P-1050. A new index for LTHA ground motion selection (Ieq) is proposed to control response variability in relation to the dynamic properties of the structure aimed at obtaining a suitable input for LTHA design. A target value for Ieq is proposed on the basis of structural response for far-field and near-field suites and an ad hoc suite of pulse-like ground motions selected considering pulse periods lower than the fundamental period of the structure. The difference in terms of design results between LTHA and RSA is employed as benchmark to evaluate the suitability of Ieq for LTHA design.

In the field of cultural heritage, UV-induced fluorescence (UVIFL) photography is extensively applied to the study of artworks. In the case of historical musical instruments (e.g. violins), this technique allows seeing important details that usually cannot be detected under visible light, such as retouching, different paint and varnish coats or worn areas of the superficial varnishes. The interpretation of UVIFL images, even when performed by expert people, may be very complex, taking into account the chemical and physical modifications undergone by the analyzed instruments during the centuries. The aim of this work is the development of a new tool able to help experts by automatically detecting the presence of worn areas on the surface of violins. The proposed algorithm is based on a specific combination of thresholding and mathematical morphology designed to detect some characteristic fluorescence colors. The system discriminates different wear levels, finds their position on the surface and computes their percentage respect to the total area. To validate our approach a collection of UVIFL images of Stradivari's violins held in the “Museo del Violino” in Cremona (Italy) was considered. The analyses of the UVIFL images taken on the back plates of the instruments provide results that are in agreement with the naked eye segmentation and classification performed by expert people (e.g. violin makers, restorers and the curator of the museum).

The aim of this work is to open up new opportunities for designers towards a performance-based approach to derive fragilities at design stage. Nonlinear Time-History Analysis (NTHA) represents the current practice for the estimation of damage within the Performance-Based Earthquake Engineering (PBEE) framework. Among the NTHA approaches for fragility assessment, Cloud Analysis (CA) represents a convenient tool which allows evaluating the parameters of the conditional demand distribution based on simple regression of cloud-dispersed data points obtained from recorded ground motions. Notwithstanding the growth in computer processing power and software development, NTHA is generally time-consuming and it requires advanced expertise in nonlinear modelling, preventing its use in the professional field at design stage. Herein, a novel procedure for deriving fragility curves built up through Linear Time-History Analysis (LTHA) and CA is presented. It can be employed within a simplified PBEE approach at design stage for performance comparison of design solutions. Differences between LTHA results and those obtained through NTHA are compared for the assessment of a 12-storey Reinforced-Concrete Moment-Resisting-Frame building designed according to Eurocode 8. Assessment is performed for two limit states: Life Safety- and Damage Limitation- Limit State. Critical aspects for LTHA-based fragility assessment such as (i) influence of ground motion suite size and (ii) identification of “unacceptable cases” are investigated. The final level of approximation of these “design-fragilities” is very satisfactory making the full approach pursuable and useful for professional applications.

Sinkholes represent a natural risk that may hit catastrophically without clearly detectible precursors. However, they are often overlooked by people and administrators. Therefore sinkhole monitoring and associated early warnings constitute important research topics but, currently, only a few papers about sinkhole prediction can be found. In this paper an experience of sinkhole monitoring and early warning with GB-InSAR is described. The latter is a highly precise instrument that is able to produce displacement maps with metric spatial resolution. The described activities were carried out on Elba Island (central Italy), where karstified limestone set off the occurrence of nine sinkholes since 2008, all within less than 3000 m2, causing major damage to an important road and many indirect losses. In 1 year of monitoring two deforming areas were detected, and the point where a sinkhole was about to propagate to the street level was predicted, thus permitting the preventive closure of the road. The deformation area was larger than the hole generated by the sinkhole, thus showing a subsidence that continued for a prolonged time even after the cavity was filled up. The occurrence of a 1.5-m-wide sinkhole, undetected by the GB-InSAR, also showed the lower detection limit of the instrument.

Late onset Pompe disease (LOPD) is characterized by significant motor disabilities, which affect in particular ambulation. Only one study reports on spatial-temporal parameters of gait assessed in a clinical heterogeneous group of unrelated patients. In this study spatiotemporal and kinematic gait patterns are described in a genetically homogenous group of LOPD patients using 3d movement analysis. 7 LOPD siblings, harbouring the same GAA mutations compound, were assessed with clinical scales and with 3d movement analysis to measure spatial-temporal and kinematic parameters during gait cycle and “sit to stand test”. Relevant abnormalities were observed either in spatial-temporal and kinematic parameters. The former consisted in a trend towards a decreased velocity and cadence, a prolonged time in double limb support, shorter step and stride length, and a widening of base of support; the latter in an increased anterior pelvic-tilt and posterior trunk-tilt during the whole gait cycle, a decreased pelvic obliquity, active hip extension and ankle dorsiflexion. This study shows, in homogenous group of LOPD patients, either spatial-temporal and kinematic deviations that may improve understanding of the musculoskeletal alterations, the evolution of disease and the answer to the enzyme replacement therapy.

In the literature, different approaches of artificial visual systems inspired to biological solutions can be found. In this paper a particular solution will be described with an experimental case study: the foveated retina approach. The solution can be considered as a proposal of ad-hoc hardware implementation of biological inspired solutions, but also as a model for the internal virtual representation of the real world structures.

Over the past few years, motivated by the accelerating technological convergence of sensing, computing and communications, there has been a growing interest in potential and technological challenges of Wireless Sensor Network. This paper will introduce a wide range of current basic research lines dealing with ad hoc networks of spatially distributed systems, data rate requirements and constraints, real-time fusion and registration of data from distributed sensors, cooperative control, hypothesis generation, and network consensus filtering. This technical domain has matured to the point where a number of industrial products and systems have appeared. The presentation will also describe the state of the art regarding current and soon-to-appear applications.

The paper reports an efficient and fully parallel 2D shape recognition method based on the use of a multiscale tree representation of the shape boundary and recursive learning of trees. Specifically, the shape is represented by means of a tree where each node, corresponding to a boundary segment at some level of resolution, is characterized by a real vector containing curvature, length, symmetry of the boundary segment, while the nodes are connected by arcs when segments at successive levels are spatially related. The recognition procedure is formulated as a training procedure made by a Fuzzy recursive neural network followed by a testing procedure over unknown tree structured patterns. The proposed neural network model is able to facilitate the exchange of information between symbolic and sub-symbolic domains and deal with structured organization of information, that is typically required by symbolic processing.

Segmentation is a fundamental step in image description or classification. In recent years, several computational models have been used to implement segmentation methods but without establishing a single analytic solution. However, the intrinsic properties of neural networks make them an interesting approach, despite some measure of inefficiency. This paper presents a clustering approach for image segmentation based on a modified fuzzy approach for image segmentation (ART) model. The goal of the proposed approach is to find a simple model able to instance a prototype for each cluster avoiding complex post-processing phases. Results and comparisons with other similar models presented in the literature (like self-organizing maps and original fuzzy ART) are also discussed. Qualitative and quantitative evaluations confirm the validity of the approach proposed.

The main limitation of state-of-the-art magnifying techniques is that they do not introduce any new information to the original image. This lack of information, more precisely the absence of high spatial frequency components is responsible for the perceptible degradation of the enlarged image. The idea underlying this work is to estimate the phases and frequencies of absent waveforms of absent frequencies from the original low resolution image and then to synthesize them in the high resolution image. The developed technique takes advantage of sub-pixel edge estimations from the low resolution image to direct the subsequent polynomial interpolation step. To improve perceptible image quality, the n-degree polynomial interpolating curve is user-controllable allowing both sharp and smooth edges to be synthesized. The proposed approach has been applied both to gray-level images and to color images.

Evolutionary algorithms are proving viable in solving complex optimization problems such as those typical of supervised learning approaches to image understanding. This paper presents an evolutionary approach to image classification and discusses some experimental results, suggesting that genetic programming could provide a convenient alternative to standard supervised learning methods.

This paper proposes the applications of the Boundary Integral–Resonant Mode Expansion (BI–RME) method to the shape analysis problem, an approach originally implemented for the determination of modes of a cavity resonator. We explore its advantages for shape analysis and recognition of a BI–RME based modal matching algorithm, where each shape is represented with a set of eigenfunctions, and solutions of the Helmholtz equation with Dirichlet boundary condition. These solutions correspond to the vibration modes of an elastic sheet of arbitrary shape and fixed boundary and show some advantages over previous approaches. It is demonstrated that the BI–RME algorithm is particularly suitable for characterizing shapes with multiply connected boundaries and requires small cpu times.

In this paper we present an efficient 2D object recognition method that uses multiscale tree representations. A planar object is represented by means of a tree, in which each node corresponds to a boundary segment at some level of resolution and an arc connects nodes corresponding to segments at successive levels that are spatially related. The problem of matching an object against a model is formulated as the one of determining the best mapping between nodes at all levels of the two associated trees. The proposed matching algorithm is based on dynamic programming and has optimal O(∣T ∣∣T′∣) time complexity, where ∣ T ∣ and ∣ T ′∣ are the number of nodes in the two trees.

In this work we propose a new page segmentation method for recognizing text and graphics based on a multiresolution representation of the page image. Our approach is based on the analysis of a set of feature maps available at different resolution levels. The final output is a description of the physical structure of a page. A page image is broken down into several blocks which represent components of a page, such as text, line-drawings, and pictures. The result, which uses only a small amount of memory in addition to that for the image, may be the first step for a more detailed analysis such as optical character recognition.

This paper presents a multiresolution approach that uses a diffusion process to describe the shape of a 2D object. As a result, shape recognition can be achieved: shape contours may be recognized independently from orientation or size. The method proposed relies on the concept of a structural coding of an object at varying levels of resolution. A tree structure represents the evolution of the contour at increasing levels of detail, where each tree node represents a contour segment via a set of attributes to provide a richer description of the image shape. The shape recognition is based on a matching of the attributed tree representation of the candidates with that of the model.

This paper describes a new method that uses the diffusion-like process to classify angles in a image. The proposed method exploits the curvature value of a contour line to characterize the correspondent angle. The effectiveness of the new method is illustrated with the results of experiments for a number different angle types.