An automatic system for the analysis of links among dream sources Barcaro U., Cavallero C., Navona C., Salvetti O. An automatic system is described for the automatic analysis of textfiles including dream reports obtained after forced awakening and associations with the dream items. The system consists of a Dictionary Database, a Result Database, and a set of Java procedures. The final result consists in tables representing multigraphs whose nodes correspond to memory sources and whose arcs correspond to links among memory sources.Source: Journal of sleep research (Print) 6 (2006).
A markov model for blind image separation by a mean-field EM algorithm Tonazzini A., Bedini L., Salerno E. This paper deals with blind separation of images from noisy linear mixtures with unknown coefficients, formulated as a Bayesian estimation problem. This is a flexible framework, where any kind of prior knowledge about the source images and the mixing matrix can be accounted for. In particular, we describe local correlation within the individual images through the use of MRF image models. These are naturally suited to express the joint pdf of the sources in a factorized form, so that the statistical independence requirements of most ICA approaches to BSS are retained. Our model also includes edge variables to preserve intensity discontinuities. MRF models have been proved to be very efficient in many visual reconstruction problems, such as blind image restoration, and allow separation and edge detection to be performed simultaneously. We propose an Expectation-Maximization algorithm with the mean field approximation, to derive a procedure for estimating the mixing matrix, the sources and their edge maps. We tested this procedure on both synthetic and real images, in the fully blind case (i.e. no prior information on mixing is exploited) and found that a source model accounting for local auto-correlation is able to increase robustness against noise, even space-variant. Furthermore, when the model closely fits the source characteristics, independence is no more a strict requirement, and cross-correlated sources can be separated as well.Source: IEEE transactions on image processing 15 (2006): 473–482. doi:10.1109/TIP.2005.860323 DOI: 10.1109/tip.2005.860323 Metrics:
An integrated infrared-visible system for fire detection Pieri G., Benvenuti M., De Michele P., Petri D., Salvetti O. The activity under investigation in this paper regards in particular the development of an information system for the automatic monitoring and detection of forest fires, using combined infrared and visible cameras. The proposed system is based on previously selected and studied algorithms. An integrated information system developed for the monitoring and the automatic detection and location of forest fires is described. This system uses robotized stations equipped with combined infrared (IR) and visible cameras. A specific approach has been developed based on computing thermal and spatial information suitably fused. Real time meteorological information, and previously stored morphological information are integrated and processed by a suitable decisional component based on a fuzzy rules system, which gives the final response for an alert on an active fire.Source: Forest ecology and management 234 (2006): S37.
An interactive musical exhibit based on infrared sensor Bertini G., Magrini M., Tarabella L. This paper deals with the description of the design of an exhibit for controlling real-time audio synthesis with a wireless, IR-based interface. Researching new way for playing and real-time controlling electronic music is today's hot topic in the computer music field. In this specific project the goal is to obtain an enjoyable exhibit playability together with robustness and reliability, in order to constantly operate with young users (children too) and, more in general, non expert people. Our effort has been focused to carefully design the hardware/software project, in a way that the final user will interact only with non critical parts of the system.Source: Lecture notes in computer science 3902 (2006): 92–100.
Estimating the spectral indices of correlated astrophysical foregrounds by a second-order statistical approach Bonaldi A., Bedini L., Salerno E., Baccigalupi C., De Zotti G. We present the first tests of a new method, the correlated component analysis (CCA) based on second-order statistics, to estimate the mixing matrix, a key ingredient to separate astrophysical foregrounds superimposed to the Cosmic Microwave Background (CMB). In the present application, the mixing matrix is parametrized in terms of the spectral indices of Galactic synchrotron and thermal dust emissions, while the free-free spectral index is prescribed by basic physics, and is thus assumed to be known. We consider simulated observations of the microwave sky with angular resolution and white stationary noise at the nominal levels for the Planck satellite, and realistic foreground emissions, with a position-dependent synchrotron spectral index. We work with two sets of Planck frequency channels: the low-frequency set, from 30 to 143 GHz, complemented with the Haslam 408 MHz map, and the high-frequency set, from 217 to 545 GHz. The concentration of intense free-free emission on the Galactic plane introduces a steep dependence of the spectral index of the global Galactic emission with Galactic latitude, close to the Galactic equator. This feature makes difficult for the CCA to recover the synchrotron spectral index in this region, given the limited angular resolution of Planck, especially at low frequencies. A cut of a narrow strip around the Galactic equator (|b| 3?), however, allows us to overcome this problem. We show that, once this strip is removed, the CCA allows an effective foreground subtraction, with residual uncertainties inducing a minor contribution to errors on the recovered CMB power spectrum.Source: Monthly notices of the Royal Astronomical Society (Print) 373 (2006): 271–279. doi:10.1111/j.1365-2966.2006.11025.x DOI: 10.1111/j.1365-2966.2006.11025.x DOI: 10.48550/arxiv.astro-ph/0609701 Metrics:
SAR image filtering based on the heavy-tailed rayleigh model Achim A., Kuruoglu E. E., Zerubia J. Synthetic aperture radar (SAR) images are inherently affected by a signal dependent noise known as speckle, which is due to the radar wave coherence. In this paper, we propose a novel adaptive despeckling filter and derive a maximum a posteriori(MAP) estimator for the radar cross section (RCS). We first employ a logarithmic transformation to change the multiplicative speckle into additive noise. We model the RCS using the recently introduced heavy-tailed Rayleigh density function, which was derived based on the assumption that the real and imaginary parts of the received complex signal are best described using the alpha-stable family of distribution.We estimate model parameters from noisy observations by means of second-kind statistics theory, which relies on the Mellin transform. Finally, we compare the proposed algorithm with several classical speckle filters applied on actual SAR images. Experimental results show that the homomorphic MAP filter based on the heavy-tailed Rayleigh prior for the RCS is among the best for speckle removal.Source: IEEE transactions on image processing 15 (2006): 2686–2693. doi:10.1109/TIP.2006.877362 DOI: 10.1109/tip.2006.877362 Metrics:
Object tracking in a stereo and infrared vision system Colantonio S., Benvenuti M., Di Bono M. G., Pieri G., Salvetti O. In this paper, we deal with the problem of real-time detection, recognition and tracking of moving objects in open and unknown environments using an infrared (IR) and visible vision system. A thermo-camera and two stereo visible-cameras synchronized are used to acquire multi-source information: three-dimensional data about target geometry and its thermal information are combined to improve the robustness of the tracking procedure. Firstly, target detection is performed by extracting its characteristic features from the images and then by storing the computed parameters on a specific database; secondly, the tracking task is carried on using two different computational approaches. A Hierarchical Artificial Neural Network (HANN) is used during active tracking for the recognition of the actual target, while, when partial occlusions or masking occur, a database retrieval method is used to support the search of the correct target followed. A prototype has been tested on case studies regarding the identification and tracking of animals moving at night in an open environment, and the surveillance of known scenes for unauthorized access control.Source: Infrared physics & technology 49 (2006): 266–271. doi:10.1016/j.infrared.2006.06.028 DOI: 10.1016/j.infrared.2006.06.028 Metrics:
HEARTFAID: a knowledge based platform for supporting the clinical management of elderly patients with heart failure Conforti D., Costanzo D., Lagani V., Perticone F., Parati G., Kawecka-Jaszcz K., Marsh A., Biniaris C., Stratakis M., Fontanelli R., Guerri D., Salvetti O., Tsiknakis M., Chiarugi F., Gamberger D., Valentini M. Chronic heart failure is a major health problem in many developed countries with strong social and economic effects due to its prevalence and morbidity. These effects occur particularly in the elderly who have frequent hospital admissions and utilise significant medical resources. Studies and data have demonstrated that evidence-based heart failure management programs utilising appropriate integration of inpatient and outpatient clinical services, have the potential to prevent and reduce hospital admissions, improve clinical status and reduce healthcare costs. HEARTFAID is a research and development project aimed at creating and validating an innovative knowledge-based platform to improve the early diagnosis and effective management of heart failure. The core of the platform is formalisation of pre-existing clinical knowledge and the discovery of new elicited knowledge. HEARTFAID has been designed to improve the processes of diagnosis, prognosis and therapy by providing the following services: Electronic health records for easy and ubiquitous access to heterogeneous patient data Integrated services for healthcare professionals, including patient telemonitoring, signal and image processing, alert and alarm systems Clinical decision support, based on pattern recognition in historical data, knowledge discovery analysis and inference from patients' clinical data.Source: The journal on information technology in healthcare 4 (2006): 283–300.
Particle swarm optimization for the reconstruction of permittivity range profiles from microwave measurements Genovesi S., Salerno E. At the Signal and Images lab, ISTI-CNR, we are developing a new algorithm to reconstruct the permittivity range profile of a layered medium from microwave backscattering data. The algorithm is based on a particle swarm strategy to optimize a specific edge-preserving objective functional. Our technique is able to efficiently find the global optimum of the objective functional, while preserving the discontinuities in the reconstructed profile.Source: ERCIM news 64 (2006): 42–43.
Analysis and modelling of genomic data Tonazzini A., Bonchi F., Gnesi S., Kuruoglu E., Bottini S. At ISTI-CNR, Pisa, researchers from different areas of computer science are studying an integrated and interdisciplinary approach to challenging problems in Computational Biology and Bioinformatics.Source: ERCIM news 64 (2006): 59–60.
A general approach to shape characterization for biomedical problems Moroni D., Perner P., Salvetti O. In this paper, we present a general approach to shape characterization and deformation analysis of 2D/3D deformable visual objects. In particular, we define a reference dynamic model, encoding morphological and functional properties of an objects class, capable to analyze different scenarios in heart left ventricle analysis. The proposed approach is suitable for generalization to the analysis of periodically deforming anatomical structures, where it could provide useful support in medical diagnosis. Preliminary results in heart left ventricle analysis are discussed.Source: Industrial Conference on Data Mining ICDM --- Workshop on Mass-Data Analysis of Images and Signals, MDA 2006, pp. 56–65, Leipzig, Germany, 13/07/2006
A method for detection of transient events in EEG signals Righi M., Starita A., Barcaro U., Erimakis S., Micheloyannis S. A method is described for the detection of EEG transient events that are characterized by transient decrease in the correlation between homologous frequency-band components of different traces. It consists of the following steps: computation of frequency-band components; computation of normalized correlation; application of two thresholds (one for the recognition of an event, and the other for the measure of the event time-length). The method also provides a classification of the detected events. The results can be subjected to statistical analyses. An application is described to seizure-free EEGs of epileptic subjects.Source: Biopattern Brain Workshop, pp. 15–16, Göteborg, 18-19/05/2006
A method to integrate thermographic data and 3D shapes for Diabetic Foot Disease Colantonio S., Pieri G., Salvetti O., Benvenuti M., Barone S., Carassale L. This paper presents the results of a project carried out within a collaboration among TD Group S.p.A., ISTI-CNR, Dept. of Mechanics, Nuclear and Production Engineering, University of Pisa, and the Diabetology Dept. at the 'San Giovanni di Dio' Hospital in Florence. The goal of this activity has been to integrate thermal information and three dimensional spatial data by combining acquisitions from a thermocamera and a stereo pair of high resolution visible cameras. An application in the medical field is presented regarding the Diabetic Foot Disease to support physicians in their diagnosis and follow-up.Source: International Conference on Quantitative InfraRed Thermography, Padova, 28-30/0672006
A minimax entropy method for blind separation of dependent components in astrophysical images Caiafa C. F., Kuruoglu E. E., Proto A. N. We develop a new technique for blind separation of potentially non independent components in astrophysical images. Given a set of linearly mixed images, corresponding to different measurement channels, we estimate the original electromagnetic radiation sources in a blind fashion. Specifically, we investigate the separation of cosmic microwave background (CMB), thermal dust and galactic synchrotron emissions without imposing any assumption on the mixing matrix. In our approach, we use the Gaussian and non-Gaussian features of astrophysical sources and we assume that CMB-dust and CMB-synchrotron are uncorrelated pairs while dust and synchrotron are correlated which is in agreement with theory. These assumptions allow us to develop an algorithm which associates the Minimum Entropy solutions with the non-Gaussian sources (thermal dust and galactic synchrotron emissions) and the Maximum Entropy solution as the only Gaussian source which is the CMB. This new method is more appropriate than ICA algorithms because independence between sources is not imposed which is a more realistic situation. We investigate two specific measures associated with entropy: Gaussianity Measure (GM) and Shannon Entropy (SE) and we compare them. Finally, we present a complete set of examples of separation using these two measures validating our approach and showing that it performs better than FastICA algorithm. The experimental results presented here were performed on an image database that simulates the measurements expected from the instruments that will operate onboard ESA's Planck Surveyor Satellite to measure the CMB anisotropies all over the celestial sphere.Source: Bayesian Inference and Maximum Entropy Methods In Science and Engineering, pp. 81, Paris, France, 08-13/07/2006
An integrated infrared-visible system for fire detection Pieri G., Benvenuti M., De Michele P., Salvetti O. The activity under investigation in this paper regards in particular the development of an information system for the automatic monitoring and detection of forest fires, using combined infrared and visible cameras. The proposed system is based on previously selected and studied algorithms.Source: International Conference on Forest Fire Research, Figueira da Foz, Coimbra - Por, 27-30/11/2006
Active video-surveillance based on stereo and infrared imaging Pieri G., Salvetti O. Video-surveillance is a very actual and critical issue at the present time. Within this topic we address the problem of firstly identifying moving people in a scene through motion detection techniques, and subsequently categorising them in order to identify humans for tracking their movements. The use of stereo cameras, coupled with infrared vision, allows to apply this technique to images acquired through different and variable condition, and allows an a priori filtering based on the characteristics of such images to give evidence to objects emitting an higher radiance (i.e. higher tempera-ture).Source: 14th European Signal Processing Conference, Florence, 04-08/09/2006
An infrastructure for multimedia metadata management Asirelli P., Martinelli M., Salvetti O. This paper presents an approach for the integration of multimedia metadata and their management based on Semantic Web technology. In par-ticular, we propose a java-based Infrastructure for MultiMedia Metadata Man-agement - 4M - composed of five main components, an MPEG-7 feature proc-essing unit, an XML database management unit, an algorithms ontology-exploiting unit, a multimedia semantic annotation and integration units. This way, we intend to introduce the novel idea of managing also algorithms on a variety of multimedia metadata (audio, images and videos) to add the capability of tracking data processing. This work is mainly carried out in the framework of the European Network of Excellence MUSCLE (Multimedia Understanding through Semantics, Computation and Learning), where ISTI-CNR is leading the 'Representation and Communication of Data and Metadata' Workpackage.Source: First International Workshop on Semantic Web Annotations for Multimedia (SWAMM 2006), pp. 1, Edinburgh, 22/05/2006
Automatic fuzzy-neural based segmentation of microscopic cell images Colantonio S., Gurevich I. B., Salvetti O. In this paper, we propose a novel, completely automated method for the segmentation of lymphatic cell nuclei represented in microscopic specimen images. Actually, segmenting cell nuclei is the first, necessary step for develop-ing an automated application for the early diagnostics of lymphatic system tu-mors. The proposed method follows a two-step approach to, firstly, find the nu-clei and, then, to refine the segmentation by means of a neural model, able to localize the borders of each nucleus. Experimental results have shown the fea-sibility of the method.Source: Workshop on Mass Data Analysis of Signals and Images, MDA 2006, pp. 34–45, Leipzig, Germany, 13/06/2006