IndianaMAS

  • Increase font size
  • Default font size
  • Decrease font size
Home External Links Previous work from the IndianaMAS partners
External Links
Display # 
# Web Link Hits
1   Link   "An open software agent society for multi-language hand drawn diagrammatic sketch recognition" by Giovanni Casella

Recognizing hand-sketched symbols is a complex problem. The input drawings are often intrinsically ambiguous, and require context to be interpreted in a correct way. Many existing sketch recognition systems avoid this problem by recognizing single segments or simple geometric shapes in a stroke. However, for a recognition system to be effective and precise, context must be exploited, and both the simplifications on the sketch features, and the constraints under which recognition may take place, must be reduced to the minimum.
The main goal of this thesis is the definition of an agent society for hand-drawn sketch interpretation that heavily exploits contextual information for ambiguity resolution. Agents manage the activity of low-level hand-drawn symbol recognizers, which may be heterogeneous for better adapting to the characteristics of each symbol to be recognized, and coordinate themselves in order to exchange contextual information, thus leading to an efficient and precise interpretation of sketches.
In order to build a flexible and extensible society we needed suitable means, from the
Agent Oriented Software Engineering (AOSE) field, to define software agents able to join the society at run-time interacting with existing agents to recognize new languages. During the research it became evident that the AOSE field did not offer any suitable tool to enhance interactions between agents not designed together which we could exploit.
To pursue the agent interaction flexibility issues and to enable new agents to join the
society at run-time bringing new capabilities, we have designed and implemented the West2East toolkit. We have defined West2East factoring three leading edge technologies, namely Intelligent Agents, Web Services, and Computational Logic. West2East offers facilities for building agents able to interact with other agents in open and dynamic systems, where interaction protocols are not known in advance, and to reason about these
interactions.

Giovanni Casella: An open software agent society for multi-language hand drawn diagrammatic sketch recognition, PhD Thesis, University of Salerno (2008)
223
2   Link   "An agent-based framework for sketched symbol interpretation" by G. Casella, V. Deufemia, V. Mascardi, G. Costagliola, M. Martelli

Recognizing hand-sketched symbols is a definitely complex problem. The input drawings are often intrinsically ambiguous, and require context to be interpreted in a correct way. Many existing sketch recognition systems avoid this problem by recognizing single segments or simple geometric shapes in a stroke. However, for a recognition system to be effective and precise, context must be exploited, and both the simplifications on the sketch features, and the constraints under which recognition may take place, must be reduced to the minimum. In this paper, we present an agent-based framework for sketched symbol interpretation that heavily exploits contextual information for ambiguity resolution. Agents manage the activity of low- level hand-drawn symbol recognizers, that may be heterogeneous for better adapting to the characteristics of each symbol to be recognized, and coordinate themselves in order to exchange contextual information, thus leading to an efficient and precise interpretation of sketches. We also present AgentSketch, a multi-domain sketch recognition system implemented according to the proposed framework. A first experimental evaluation has been performed on the domain of UML Use Case Diagrams to verify the effectiveness of the proposed approach.

Giovanni Casella, Vincenzo Deufemia, Viviana Mascardi, Gennaro Costagliola, Maurizio Martelli: An agent-based framework for sketched symbol interpretation. J. Vis. Lang. Comput. 19(2): 225-257 (2008)

DBLP: http://www.informatik.uni-trier.de/~ley/db/journals/vlc/vlc19.html#CasellaDMCM08
137
3   Link   "Reasoning about Hand-Drawn Sketches: An Approach Based on Intelligent Software Agents" by G. Casella, V. Deufemia, V. Mascardi, M. Martelli, G. Tortora

Sketching is a powerful means to represent objects and reason on them. In this paper we describe an integrated environment, conceived as a multi agent system, that brings together sketch recognition functionalities and decision support facilities. In this environment, intelligent agents are exploited both for managing the process of recognition of the sketched objects, and for supporting users in solving decisional problems. We explain our approach and its potential by means of a running example taken from the domain of building's safety.

Giovanni Casella, Vincenzo Deufemia, Viviana Mascardi, Maurizio Martelli, Genoveffa Tortora: Reasoning about Hand-Drawn Sketches: An Approach Based on Intelligent Software Agents. VISUAL 2008: 302-314 (2008)

DBLP: http://www.informatik.uni-trier.de/~ley/db/conf/visual/visual2008.html#CasellaDMMT08
212
4   Link   "A Multi-Agent System for Hand-drawn Diagram Recognition" by G. Casella, V. Deufemia, V. Mascardi

In this paper we present AgentSketch, an agent-based system for on-line recognition of hand-drawn diagrams. Agents are used for managing the activity of symbol recognizers and for providing efficient interpretations of the sketch to the user thanks to the use of contextual information for ambiguity resolution. The system can be applied to a variety of domains by providing recognizers of the symbols in that domain. A first experimental evaluation has been performed on the domain of UML use case diagrams to verify the effectiveness of the proposed approach.

Giovanni Casella, Vincenzo Deufemia, Viviana Mascardi: A Multi-Agent System for Hand-drawn Diagram Recognition. ICDAR 2007: 739-743 (2007)

DBLP: http://www.informatik.uni-trier.de/~ley/db/conf/icdar/icdar2007.html#CasellaDM07
143
5   Link   "An Agent-Based Framework for Context-Driven Interpretation of Symbols in Diagrammatic Sketches" by G. Casella, G. Costagliola, V. Deufemia, M. Martelli, V. Mascardi

Parsing hand-drawn diagrams is a definitely complex recognition problem. The input drawings are often intrinsically ambiguous, and require context to be interpreted in a correct way. Many existing sketch recognition systems avoid this problem by recognizing single segments or simple geometric shapes in a stroke. However, for a recognition system to be effective and precise, context must be exploited, and both the simplifications on the sketch features, and the constraints under which recognition may take place, must be reduced to the minimum. In this paper we present an agent-based framework for context-driven interpretation of symbols in diagrammatic sketches that heavily exploits contextual information for ambiguity resolution. Agents manage the activity of low-level hand-drawn symbol recognizers, that may be heterogeneous for better adapting to the characteristics of each symbol to be recognized, and coordinate themselves in order to exchange contextual information, thus leading to an efficient and precise interpretation of sketches.

Giovanni Casella, Gennaro Costagliola, Vincenzo Deufemia, Maurizio Martelli, Viviana Mascardi: An Agent-Based Framework for Context-Driven Interpretation of Symbols in Diagrammatic Sketches. VL/HCC 2006: 73-80 (2006)

DBLP: http://www.informatik.uni-trier.de/~ley/db/conf/vl/vlhcc2006.html#CasellaCDMM06
159
6   Link   "MANENT: An Infrastructure for Integrating, Structuring and Searching Digital Libraries" by A. Locoro, D. Grignani, V. Mascardi
Digital Libraries represent the commitment of research communities to preserve authoritative and well structured sources of knowledge, and to share archival organisations, methods and resources thanks to systems relying on standard metadata formats. This chapter describes some natural language processing techniques exploited for automatically extracting structural information about documents stored in Digital Libraries, based on the exposed metadata. The most prominent results achieved in this area are surveyed and discussed. As an example of infrastructure for integrating, structuring and searching Digital Libraries based on natural language processing and semantic web techniques, we discuss the MANENT system. MANENT is a working prototype offering services of Digital Library content management and record classification and retrieval. It is hosted on a server at the CS Department of Genova University and, starting from 2011, it will become publicly available. 475,000 records drawn from 138 repositories that all over the world expose OAI-PMH services have been downloaded, stored, and part of them has been already automatically classified by MANENT.

Angela Locoro, Daniele Grignani, Viviana Mascardi: MANENT: An Infrastructure for Integrating, Structuring and Searching Digital Libraries. In Learning Structure and Schemas from Documents. M. Biba and F. Xhafa, editors, Springer-Verlag. Studies in Computational Intelligence serie, volume 375, pages 315-342, 2011.

183
7   Link   "When you Doubt, Abstain: from Misclassification to Epochè in Automatic Text Categorisation" by A. Locoro, D. Grignani, V. Mascardi
This paper describes how natural language processing and ontologies are exploited for automatic text categorisation. The approach introduced is part of the MANENT system, an infrastructure for integrating, structuring and searching Digital Libraries. The procedure of structural information extraction, and of the automatic classification of the records according to natural language understanding and the WordNet Domains taxonomy is discussed. A comparison between two versions of the classification algorithm is conducted and the improvements of the new approach are articulated. In particular, using semantic connections between words refines the classification results while reducing misclassification to non classification.

Angela Locoro, Daniele Grignani, Viviana Mascardi: When you Doubt, Abstain: from Misclassification to Epochè in Automatic Text Categorisation. In Jomi Fred Hubner, Jean-Marc Petit, Einoshin Suzuki (Eds.): Proceedings of the 2011 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT 2011. IEEE Computer Society, pag. 209-212, 2011.

DBLP: http://dblp.uni-trier.de/rec/bibtex/conf/iat/LocoroGM11
161
8   Link   "Agents and Ontologies for Understanding and Preserving the Rock Art of Mount Bego" by L. Papaleo, G. Quercini, V. Mascardi, M. Ancona, A. Traverso, H. De Lumley
This paper describes the joint effort of computer scientists, archaeologists, and historians for designing a multi-agent system that exploits ontologies for the semantic description of the Mount Bego petroglyphs, thus moving a step forward their preservation. Most components of the MAS have already been developed and tested, and their integration is under way.

Laura Papaleo, Gianluca Quercini, Viviana Mascardi, Massimo Ancona, A. Traverso, H. De Lumley: Agents and Ontologies for Understanding and Preserving the Rock Art of Mount Bego. In Joaquim Filipe, Ana L. N. Fred (Eds.): ICAART 2011 - Proceedings of the 3rd International Conference on Agents and Artificial Intelligence, Volume 2 - Agents pag. 288-295, 2011

DBLP: http://www.dblp.org/rec/bibtex/conf/icaart/PapaleoQMATL11

155
9   Link   "Virtual Institutions for Preserving and Simulating the Culture of Mount Bego's Ancient People" by M. Ancona, V. Mascardi, G. Quercini, A. Bogdanovych, H. De Lumley, L. Papaleo, S. Simoff, A. Traverso
The Alps of southeastern France, better known as the Valley of Marvels, hide an impressive collection of engravings, mostly visible on the rocks around Mount Bego, which are irreplaceable witnesses of what life of the people who created them looked like. This calls for immediate action on promoting the awareness of this cultural treasure, which is hardly accessible by interested common men, as well as on helping domain experts to analyze these engravings and share their understanding and theories about them with other experts and with the mass. In this position paper, we propose technologies and partially achieved results for preserving in digital form all kinds of available data about the region. The technology will allow domain experts to: (i) organize and structure data into an existing collaborative tool set, (2) process them, (3) make assumptions about the way of life of the ancient people based on them, and (4) make the results of such activities available in form of 3D Virtual Worlds.

M. Ancona, V. Mascardi, G. Quercini, A. Bogdanovych, H. De Lumley, L. Papaleo, S. Simoff, A. Traverso: Virtual Institutions for Preserving and Simulating the Culture of Mount Bego's Ancient People. VAST10: The 11th International Symposium on Virtual Reality, Archaeology and Intelligent Cultural Heritage - Short and Project Papers. Short and Project Papers:5-8.
150
10   Link   "Integrating Agents and Virtual Institutions for Sharing Cultural Heritage on the Web" by A. Bogdanovych, L. Papaleo, M. Ancona, V. Mascardi, G. Quercini, S. Simoff, A. Cohen, A. Traverso
This work outlines the research activities carried out by our groups in the direction of the implementation of a tool for sharing natural and cultural heritage on the web. The tool will serve as a support to teachers and people involved in scientific and cultural activities (for example, archaeologists, historians, geologists, directors of museums and of exhibitions) for making historical, naturalistic, artistic content available in a game-like but scientifically well founded way based on Virtual Institutions and intelligent software agents. Our approach is illustrated on the example of the city of Uruk, which is believed to be the first city on Earth, where the culture of ancient Sumerians is preserved in terms of the natural environment, human behaviour and architecture.

A. Bogdanovych, L. Papaleo, M. Ancona, V. Mascardi, G. Quercini, S. Simoff, A. Cohen, A. Traverso: Integrating Agents and Virtual Institutions for Sharing Cultural Heritage on the Web. In Proceedings of the Workshop On Intelligent Cultural Heritage (Satellite workshop of the AI*IA 2009: International Conference of the Italian Association for Artificial Intelligence), Reggio Emilia, Italy, 12 December 2009.

156

Statistics

Members : 5
Content : 47
Web Links : 29
Content View Hits : 26924

Who is online

We have 69 guests online