D7net Mini Sh3LL v1
| Current File : /var/www/html/cvprlab/css/../research/index.xml |
<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
<channel>
<title>Researches | CVPR Lab</title>
<link>/research/</link>
<atom:link href="/research/index.xml" rel="self" type="application/rss+xml" />
<description>Researches</description>
<generator>Source Themes Academic (https://sourcethemes.com/academic/)</generator><language>en-us</language><lastBuildDate>Wed, 14 Nov 2018 19:02:50 -0700</lastBuildDate>
<image>
<url>/img/logo.png</url>
<title>Researches</title>
<link>/research/</link>
</image>
<item>
<title>Biological and biomedical data and image analysis</title>
<link>/research/biological/</link>
<pubDate>Wed, 14 Nov 2018 19:02:50 -0700</pubDate>
<guid>/research/biological/</guid>
<description><h2 id="biological-and-biomedical-data-and-image-analysis"><strong>Biological and biomedical data and image analysis</strong></h2>
<hr>
<p>The Group was involved in research to design of machine learning and soft computing based techniques for biological and biomedical data and image analysis:
\</p>
<!-- raw HTML omitted -->
<ul>
<li>
<p>analysis of brain and skeletal NMR and TAC images. The careful delineation of the medical objects alone provides relevant clinical information and the extraction of quantitative features is fundamental, once the diagnosis was made, to determine the extent and progression of the disease. The activities concern the development of techniques based on artificial vision and fuzzy pattern recognition of shapes to detect anomalies in magnetic resonance and tomographic images.</p>
</li>
<li>
<p>analysis of cardio-vascular eco images. The cardiovascular and cerebrovascular diseases are the major causes of mortality in the population and the complex inner-media (IMT) of the carotid artery can be used to predict cardiovascular events such as myocardial infarction. Since the manual analysis is tiring, does not guarantee reproducibility and does not allow the analysis of other important statistics, activity concerns the development of a CAD (Computer Aided Diagnosis) based on deformable models to automatically extract the characteristics of the intimate media structure from images of the carotid artery.</p>
</li>
<li>
<p>analysis of images in functional genomics. The data of functional genomics, typically images and sequences of images, tend to identify the mechanisms that regulate the activation or deactivation of genes in various experimental conditions, such as outbreaks of diseases or sequences of observations in therapeutic phases. The activities concern the development of CAD based on Bayesian techniques to extract the activation parameters of genes and proteins, addressing issues such as gridding, the segmentation of microarray images, image registration in proteomics and image analysis in biology cellular.</p>
</li>
</ul>
<p>\</p>
<!-- raw HTML omitted -->
</description>
</item>
<item>
<title>Intelligent Processing of Spatio-temporal signals</title>
<link>/research/intelligent/</link>
<pubDate>Wed, 14 Nov 2018 19:02:50 -0700</pubDate>
<guid>/research/intelligent/</guid>
<description><h2 id="intelligent-processing-of-spatio-temporal-signals"><strong>Intelligent Processing of Spatio-temporal signals</strong></h2>
<hr>
<!-- raw HTML omitted -->
<ul>
<li>
<p>Clustering, that is discovery of groups of &ldquo;similar&rdquo; trajectories. As an example, the cluster of trajectories they can bring to light the presence of paths not adequately covered from the public transit service.</p>
</li>
<li>
<p>Frequent pattern, that is the discovery of frequent paths. These information could be useful for the city planning, as an example, evidencing frequently covered paths followed by vehicles, that could be the result of planning of the devoid traffic.</p>
</li>
<li>
<p>Classification, that is the discovery of behaviour rules, aiming to explain the behaviour of the running customers and to foretell that one of the future customers. An application could be the pre-allocation of resources.</p>
</li>
</ul>
<p><br>
From the methodological standpoint, the research activity investigates machine learning approaches and specifically neuro-fuzzy models.
\</p>
<!-- raw HTML omitted -->
</description>
</item>
<item>
<title>Soft Computing In Image Analysis</title>
<link>/research/soft/</link>
<pubDate>Wed, 14 Nov 2018 19:02:50 -0700</pubDate>
<guid>/research/soft/</guid>
<description><h2 id="soft-computing-in-image-analysis"><strong>Soft Computing In Image Analysis</strong></h2>
<hr>
<p>The rise of several major seminal theories proposed in early 60’s including fuzzy logic, genetic algorithms,
evolutionary computation, neural networks and their combination (the soft-computing paradigm in brief) allows to
incorporate imprecision and incomplete information, and to model very complex systems, making them a useful tool in
many scientific areas. These new methods may become more effective and powerful in real-world applications and can
offer viable and effective solutions to some of the most difficult problems in image and pattern analysis.
The research activity concerns the design of a computational model that takes advantage of the notion of rough
fuzzy sets and learning to realize a system capable to efficiently cluster data coming from computer vision tasks.
The hybrid notion of rough fuzzy sets comes from the combination of two models of uncertainty like vagueness by
handling rough sets (Pawlak, 1985) and coarseness by handling fuzzy sets (Zadeh, 1975). Rough sets embody the idea
of indiscernibility between objects in a set, while fuzzy sets model the ill-definition of the boundary of a
sub-class of this set. Marrying both notions lead to consider, as instance, approximation of sets by means of
similarity relations or fuzzy partitions. The proposed multiscale mechanism, based on a model of rough fuzzy
sets is adopted to spread out local into more global information. The local features extracted by the consecutive
layers are combined in the output layer in order to cluster the output neurons by minimizing the fuzziness of the
output layer. This consitutes a fast algorithm for computing scale spaces, and apply them to image processing.
We report results for region-based image segmentation and edge detection by minimizing measures of fuzziness,
while texture segmentation is realized by optimizing parabolic-evolutive partial differential equations with edge
preserving smoothing properties. An efficient block coding scheme is also designed upon the rough-fuzzy model,
together with the adoption of machine learning techniques for vector quantization, as compared against Fuzzy
Transform and Fuzzy Relational techniques.<br>
The rough-fuzzy synergy is also adopted to better represent the uncertainty in colour image representation and
histogram based indexing mechanisms.
<br>
\</p>
<!-- raw HTML omitted -->
</description>
</item>
<item>
<title>Structured Pattern Recognition</title>
<link>/research/structured/</link>
<pubDate>Wed, 14 Nov 2018 19:02:50 -0700</pubDate>
<guid>/research/structured/</guid>
<description><h2 id="structured-pattern-recognition"><strong>Structured Pattern Recognition</strong></h2>
<hr>
<table>
<thead>
<tr>
<th></th>
<th></th>
</tr>
</thead>
<tbody>
<tr>
<td><img src="/img/structured.png" alt="spr-image"></td>
<td><!-- raw HTML omitted -->In machine learning, very powerful and efficient methods have been proposed when data are represented by flat and fixed-width real vectors, even when heavily corrupted by noise. Neural networks, support vector machines and statistical methods are well known and widely used techniques. All of them share many successful stories in real-life problems, a well established theoretical background, and many journals and conferences devoted to explore possible refinements and applications. Unfortunately, in many relevant applications, data are not naturally expressed in terms of flat vectors. More expressive data structures, as trees or graphs, often nicely capture essential properties of the problem at hand, simplifying its mathematical representation and paving the way for its solution. Also, the features characterizing the input vectors are quantitative, i.e. numerical in nature, but features having imprecise or incomplete specification are usually either ignored or discarded from the design and test sets. The concept of Zadeh's fuzzy set theory can be introduced into the machine learning process to cope with impreciseness arising from various sources. For example, it may become convenient to use linguistic variables and hedges (small, medium, high, very, more and less, etc.) in order to describe the feature information. Again, uncertainty in classification may arise from the overlapping nature of classes; realistically speaking, the feature vector characterizing a specific pattern can and should be allowed to have degrees of membership in more than one class. The research activity concerns the design of neuro-fuzzy and kernels models for processing structured data. The studies relating the insertion of fuzzy rule-based domain knowledge and hence the fuzzy automaton state transitions into neural or kernel models should provide two benefits: (i) improving generalization to new instances and (ii) simplifying learning. The applications include 2D e 3D object recognition.\</td>
</tr>
<tr>
<td>\</td>
<td></td>
</tr>
</tbody>
</table>
<!-- raw HTML omitted -->
</description>
</item>
<item>
<title>Video Surveillance</title>
<link>/research/video/</link>
<pubDate>Wed, 14 Nov 2018 19:02:50 -0700</pubDate>
<guid>/research/video/</guid>
<description><h2 id="video-surveillance"><strong>Video surveillance</strong></h2>
<hr>
<table>
<thead>
<tr>
<th></th>
<th></th>
</tr>
</thead>
<tbody>
<tr>
<td><img src="/img/camera.jpg" alt="vs-image"></td>
<td><!-- raw HTML omitted -->The activity concerns the analysis, design and implementation of machine learning methods for the detection, tracking and real-time recognition of objects in motion sequences, also in mobile environments. Concerning real-time support, extensions of a video surveillance system have been proposed to make possible to guarantee speedup very close to the ideal, while improving the accuracy of the results detection. The extensions include the design of parallelization techniques at instruction-level, by SSE2, of the main computational cores and the real-time support to the operating systems to reduce jittering in video mobile transmission. Detection is dealt by proposing an approach based on self organization through artificial neural networks, widely applied in human image processing systems and more generally in cognitive science. The approach, adopted as basis to model either background and foreground, can handle scenes containing moving backgrounds, camouflage and gradual illumination variations, can include into the background model shadows cast by moving objects, and achieves robust detection for different types of videos taken with stationary cameras. Moreover, for object tracking we propose an Artificial Intelligence approach to improve correct estimates, that suitably combines Particle filtering and a matching model belonging to the class of Multiple Hypothesis Testing.</td>
</tr>
<tr>
<td>\</td>
<td></td>
</tr>
</tbody>
</table>
<!-- raw HTML omitted -->
</description>
</item>
<item>
<title>Blockchain</title>
<link>/research/blockchain/</link>
<pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
<guid>/research/blockchain/</guid>
<description><p>The Blockchain Group is composed of three elements:</p>
<ul>
<li>Dr. Alessio Ferone (assistant professor)</li>
<li>Luigi Borchia (Master student)</li>
<li>Antonio Della Porta (Master student)</li>
</ul>
<p>The activities of the group concern the study and the analysis of blockchain based systems in different application fields.<br>
A first project has been developed with the Municipality of Naples with the aim of building a metropolitan consortium blockchain to deliver services to citizens by means of utility tokens. As use case, an adaptive discount token has been implemented along with a decentralized marketplace. This project has been the argument of a Bachelor Thesis awarded by Municipality of Naples.<br>
Another application field concerns cryptocurrencies and their handling in a mobile context. The aim of the project is to integrate hardware wallets and mobile wallet exploiting NFC technology. A first outcome of this project, described in a Bachelor Thesis, is the development of two mobile apps that, hopefully, will be released to the community.<br>
Another research interest of the group concerns the use of the blockchain technology in the context of logistics and, in particular, global shipping supply chain for maritime applications.</p>
</description>
</item>
<item>
<title>Digital Film Restoration</title>
<link>/research/digital/</link>
<pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
<guid>/research/digital/</guid>
<description><h2 id="digital-film-restoration"><strong>Digital Film Restoration</strong></h2>
<hr>
<p>Activities concern several aspects of digital film restoration, including the analysis of issues related to the
problem, ranging from the kind of different defects, to their causes, and to methods and algorithms for their
removal. Particular attention is given to some specific types of defects that can affect digital image sequences
and to methodologies adopted for their management, devising new machine learning based algorithms and methodologies
for their removal. Defects taken into consideration include dust and dirt and linear scratches.<br>
We have proposed methods for automatic removal of linear scratches in digital image sequences, based on the idea of
adopting an image model as simple as possible, evaluate the displacement of such model from the real model, and
correct scratch removal through the addition of the computed displacement.<br>
Moreover, we devised a method for the detection and the removal of linear blue scratches that affect also modern
color movies, based on specific characteristics of such kind of defect.<br>
We also proposed a new methodology for the solution of classes of problems related to digital film restoration
that is well suited for implementation into high-performance parallel and distributed computing environments. The
basic idea is to adopt several well settled algorithms for the class of problems at hand, and to combine obtained
results through the adoption of suitable image fusion techniques, with the aim of taking advantage of adopted
algorithms potentialities and at the same time reducing their disadvantages.<br>
Finally, for dust and blotch removal, a novel approach was envisaged, based on viewing the problem as one of
separating overlapping images, and then reformulating it as a Blind Separation problem, approached through
Independent Component Analysis techniques. See links to: - GC06BlueScratches: Page created in order to show the
images used for testing of the blue scratch detection and removal algorithms presented in [7] and [8].</p>
<ul>
<li>BlueScratches: Page created in order to show the images used for testing of the blue scratch detection and
removal algorithms presented in [8]. - DataFusionScratches: Page created in order to show the images used for
testing of the scratch detection and removal algorithm presented in [9].</li>
</ul>
<h3 id="papers-on-digital-film-restoration">Papers on Digital Film Restoration</h3>
<p>[1] L. Maddalena, <a href="https://ieeexplore.ieee.org/document/957067Efficient">Methods for Scratch Removal in Image Sequences</a> , in Proceedings of 11th International Conference on Image Analysis and Processing (ICIAP2001), IEEE Computer Society, ISBN 0-7695-1183-X, DOI 10.1109/ICIAP.2001.957067, pp 547-552, 2001.</p>
<p>[2] G. Laccetti, L. Maddalena, A. Petrosino, Parallel/Distributed Film Line Scratch Restoration by Fusion Techniques, A. Laganà et al. (eds.), “Computational Science and its Applications – ICCSA 2004”, Lecture Notes in Computer Science, n. 3044, Springer, ISBN 3-540-22056-9, DOI 10.1007/b98051, pp. 524-534, 2004.</p>
<p>[3] G. Laccetti, L. Maddalena, A. Petrosino, P-LSR: A Parallel Algorithm for Line Scratch Restoration, in Proceedings of the Seventh International Workshop on Computer Architecture for Machine Perception (CAMP2005), IEEE Computer Society, ISBN 0-7695-2255-6, pp. 225-230, 2005.</p>
<p>[4] G. Laccetti, L. Maddalena, A. Petrosino, Removing Line Scratches in Digital Image Sequences by Fusion Techniques, in F. Roli e S. Vitulano (eds), 13th International Conference on Image Analysis and Processing (ICIAP2005), Lecture Notes in Computer Science, n. 3617, Springer-Verlag Berlin Heidelberg, pp. 695-702, DOI 10.1007/11553595_85, 2005.</p>
<p>[5] L. Maddalena, A. Petrosino, A New Methodology for Line Scratch Restoration, in Summaries of &ldquo;VIII Congresso Nazionale della SIMAI&rdquo;, p. 210, 2006.</p>
<p>[6] L. Maddalena, Recent Developments in Digital Film Restoration, in C. D’Amico (Ed.), Innovazioni Tecnologiche per i Beni Culturali in Italia, Patron Editore, ISBN 88-555-2886-6, 2006.</p>
<p>[7] L. Maddalena, A. Petrosino, A Comparison of Algorithms for Blue Scratch Removal in Digital Images, in A. Rizzi (Ed.), Colore e colorimetria: contributi multidisciplinari, vol. II, SIOF, ISBN-10 88-7957-252-0, pp. 133-144, 2006.</p>
<p>[8] L. Maddalena, A. Petrosino, Restoration of Blue Scratches in Digital Image Sequences, Image and Vision Computing, Vol. 26, Elsevier, The Netherlands, pagg. 1314–1326, 2008.</p>
<p>[9] L. Maddalena, A. Petrosino, G. Laccetti, A Fusion-based Approach to Digital Movie Restoration, Pattern Recognition, DOI 10.1016/j.patcog.2008.10.026, Vol. 42, no. 7, pagg. 1485-1495, 2009.</p>
<!-- raw HTML omitted -->
</description>
</item>
</channel>
</rss>
AnonSec - 2021 | Recode By D7net