1,721,047 research outputs found
Context Modelling Approaches for Mobile Systems
No full textThe actual mobile technology and the increasing need to obtain rich multimedia content about each
and every aspect of the human life are changing the approach of the users to the World Wide Web.
Indeed, the pervasive use of mobile devices and the heterogeneity of the provided services and information
make the accessibility and usability of the Web resources a hard assignment. In particular two
main tasks have been identified as focal issues, the first one regards the choose of a suitable model to
express the complex activities of the Web (context modeling approaches), and the second one regards
the translation of the different schemas, representing these Web activities, in a more suitable, manageable
and standardizing schema. In this chapter we will present the problems related to the modeling of
context data, and we will describe the actual and future approaches of Context Modeling according to
the mobile devices world
Sketch Style Recognition in Human Computer Interaction
No full textSketch-based interaction enables users' simple communication and it is used to represent concepts and commands in humancomputer interaction. This communication approach can be used in different contexts with different devices. The ink style through which the user performs a sketch is a critical component in the recognition and interpretation processes. In particular, the different users' styles adopted to perform the sketch can introduce over-tracing and/or cross-hatching phenomena that are respectively represented in the sketch like bold style or dashed style. The paper provides an approach to recognize the different ink styles performed by a user during his/her sketch activity. More specifically an approach to recognize both a single stroke style and the whole sketch style is presented. Copyright © (2007) by Knowledge Systems Institute (KSI)
Encephalic NMR image analysis by textural interpretation
No full textThe novel technologies used in different application domains allow to obtain digital images with a high complex informative content. These meaningful information are expressed by textural skin that covers the objects represented inside the images. The textural information can be exploited to interpret the semantic meaning of the images themselves. This paper provides a mathematical characterization, based on texture analysis, of the basic objects contained in the layout of the NMR encephalic images (cerebral tissue, rest of skull, eventual abnormal mass, and background). By this characterization a prototype has been developed, which has allowed the achievement of three different targets: segmentation of the image layout in basic objects, identification of the eventual abnormal masses, characterization of the morphologic structures of the cerebral tissue. Copyright 2008 ACM.The novel technologies used in different application domains allow to obtain digital images with a high complex informative content. These meaningful information are expressed by textural skin that covers the objects represented inside the images. The textural information can be exploited to interpret the semantic meaning of the images themselves. This paper provides a mathematical characterization, based on texture analysis, of the basic objects contained in the layout of the NMR encephalic images (cerebral tissue, rest of skull, eventual abnormal mass, and background). By this characterization a prototype has been developed, which has allowed the achievement of three different targets: segmentation of the image layout in basic objects, identification of the eventual abnormal masses, characterization of the morphologic structures of the cerebral tissue. Copyright 2008 ACM
Fusing depth and colour information for human action recognition
No full textIn recent years, human action recognition systems have been increasingly developed to support a wide range of application areas, such as surveillance, behaviour analysis, security, and many others. In particular, data fusion approaches that use depth and colour information (i.e., RGB-D data) seem to be particularly promising for recognizing large classes of human actions with a high level of accuracy. Anyway, existing data fusion approaches are mainly based on feature fusion strategies, which tend to suffer of some limitations, including the difficult of combining different feature types and the management of missing information. To address the two problems just reported, we propose an RGB-D data based human action recognition system supported by a decision fusion strategy. The system, starting from the well-known Joint Directors of Laboratories (JDL) data fusion model, analyses human actions separately for each channel (i.e., depth and colour). The actions are modelled as a sum of visual words by using the traditional Bag-of-Visual-Words (BoVW) model. Subsequently, on each channel, these actions are classified by using a multi-class Support Vector Machine (SVM) classifier. Finally, the classification results are fused by a Naive Bayes Combination (NBC) method. The effectiveness of the proposed system has been proven on the basis of three public datasets: UTKinect-Action3D, CAD-60, and LIRIS Human Activities. Experimental results, compared with key works of the current state-of-the-art, have shown that what we propose can be considered a concrete contribute to the action recognition field
Medical Image Analysis Through A Texture Based Computer Aided Diagnosis Framework
No full text"Current medical imaging scanners allow to obtain high resolution digital images with a complex. informative content expressed by the textural aspect of the membranes covering organs and. tissues (hereinafter objects). These textural information can be exploited to develop a descriptive. mathematical model of the objects to support heterogeneous activities within medical field. This. paper presents a framework based on the texture analysis to model the objects contained in the. layout of diagnostic images. By each specific model, the framework automatically also defines a. connected application supporting, on the related objects, different targets, such as: segmentation,. mass detection, reconstruction, and so on. The framework is tested on MRI images and results. are reported.
Intelligent Multi-Agent Based Information Management Methods to Direct Complex Industrial Systems
No full textIn recent years, the increasingly complexity of the logistic and technical aspects of the novel manufacturing environments, as well as the need to increase the performance and safety characteristics of the related cooperation, coordi-nation and control mechanisms is encouraging the development of new information management strategies to direct and man- age the automated systems involved in the manufacturing processes. The Computational Intelligent (CI) approaches seem to provide an effective support to the challenges posed by the next generation industrial systems. In particular, the Intelligent Agents (IAs) and the Multi-Agent Systems (MASs) paradigms seem to provide the best suitable solutions. Autonomy, flexibility and adaptability of the agent-based technology are the key points to manage both automated and information processes of any industrial system. The paper describes the main features of the IAs and MASs and how their technology can be adapted to support the current and next generation advanced industrial systems. Moreover, a study of how a MAS is utilized within a productive process is depicted
Medical Image Analysis Through a Texture Based Computer Aided Diagnosis Framework
No full textCurrent medical imaging scanners allow to obtain high resolution digital images with a complex
informative content expressed by the textural aspect of the membranes covering organs and
tissues (hereinafter objects). These textural information can be exploited to develop a descriptive
mathematical model of the objects to support heterogeneous activities within medical field. This
paper presents a framework based on the texture analysis to model the objects contained in the
layout of diagnostic images. By each specific model, the framework automatically also defines a
connected application supporting, on the related objects, different targets, such as: segmentation,
mass detection, reconstruction, and so on. The framework is tested on MRI images and results
are reported
Intelligent Multi-Agent Based Information Management Methods to Direct Complex Industrial Systems
No full text"In recent years, the increasingly complexity of the logistic and technical aspects of the novel manufacturing environ- ments, as well as the need to increase the performance and safety characteristics of the related cooperation, coordination and control mechanisms is encouraging the development of new information management strategies to direct and man- age the automated systems involved in the manufacturing processes. The Computational Intelligent (CI) approaches seem to provide an effective support to the challenges posed by the next generation industrial systems. In particular, the Intelligent Agents (IAs) and the Multi-Agent Systems (MASs) paradigms seem to provide the best suitable solutions. Autonomy, flexibility and adaptability of the agent-based technology are the key points to manage both automated and information processes of any industrial system. The paper describes the main features of the IAs and MASs and how their technology can be adapted to support the current and next generation advanced industrial systems. Moreover, a study of how a MAS is utilized within a productive process is depicted.
Design of a Framework for Personalised 3D Modelling from Medical Images
No full textIn two previous works, we introduced 3D Bio-IPF, a general purpose framework to support the three-dimensional reconstruction, rendering and processing of biomedical images. Moreover, one of its structured components, the Implant plug-in, to model customised dental implants on a three-dimensional representation of the oral cavity derived from diagnostic images has also been presented. In this paper, we provide final details of the 3D Bio-IPF framework and, at the same time, we complete the description of the Implant plug-in. We used Implant to evaluate different functionalities of the whole framework, and a characteristic result chosen among these carried out is reported. Results show that the framework and the linked plug-in are very effective for dental surgery planning, implant design and positioning. Moreover, if integrated with a position indicator system and a numerically positionable drilling machine, the system could be employed for semi-automatic surgery
Design of a framework for personalised 3D modelling from medical images
No full textIn two previous works, we introduced 3D Bio-IPF, a general purpose framework to support the three-dimensional reconstruction, rendering and processing of biomedical images. Moreover, one of its structured components, the Implant plug-in, to model customised dental implants on a three-dimensional representation of the oral cavity derived from diagnostic images has also been presented. In this paper, we provide final details of the 3D Bio-IPF framework and, at the same time, we complete the description of the Implant plug-in. We used Implant to evaluate different functionalities of the whole framework, and a characteristic result chosen among these carried out is reported. Results show that the framework and the linked plug-in are very effective for dental surgery planning, implant design and positioning. Moreover, if integrated with a position indicator system and a numerically positionable drilling machine, the system could be employed for semi-automatic surgery
- …
