An Agent-Based Multimodal Interface for Sketch Interpretation

Azar, Sleiman; Couvreur, Laurent; Delfosse, V.; Jaspart, B.; Boulanger, Cati

doi:10.1109/mmsp.2006.285357

Cited by 14 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Thus, the sequence of vertical lines is recognized as a hatch mark. In [44], Azar et al extend the previous multi-agent architecture with the possibility of interpreting also vocal information. The graphical inputs are interpreted by either rulebased agents or model-based agents, while the spoken inputs are interpreted by modelbased vocal agents.…”

Section: Related Workmentioning

confidence: 99%

An agent-based framework for sketched symbol interpretation

Casella

Deufemia

Mascardi

et al. 2008

Journal of Visual Languages & Computing

View full text Add to dashboard Cite

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 lowlevel 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. r

show abstract

Section: Related Workmentioning

confidence: 99%

An agent-based framework for sketched symbol interpretation

Casella

Deufemia

Mascardi

et al. 2008

Journal of Visual Languages & Computing

View full text Add to dashboard Cite

show abstract

“…So do Mackenzie et al [20] in order to classify sketches of animals. Other examples can be found in Azar et al [21], who base their system for sketch interpretation on agents, or in Casella et al [22], who interpret sketched symbols using an agent-based system.…”

Section: Introductionmentioning

confidence: 99%

An Agent-Based Paradigm for Free-Hand Sketch Recognition

Fernández-Pacheco

Conesa

Contero

2009

AI*IA 2009: Emergent Perspectives in Artificial Intelligence

View full text Add to dashboard Cite

Abstract. Natural interfaces for CAD applications based on sketching devices have been explored to some extent. Former approaches used techniques to perform the recognition process like invariant features extracted with image analysis techniques as neural networks, statistical learning or fuzzy logic. Currently, more flexible and robust techniques are being introduced, which consider other information as context data and other relationships. However, this kind of interfaces is still scarcely extended because they still lack scalability and reliability for interpreting user inputs.

show abstract

“…Also Mackenzie and Alechina (2003) turn to multi-agent systems in order to classify sketches of animals. Other examples can be found by Azar, Couvreur, Delfosse, Jaspart, and Boulanger (2006), who base their system for sketch interpretation on agents, or by Casella, Deufemia, Mascardi, Gennaro, and Martelli (2008), who interpret sketched symbols using an agent-based system. Finally, Hong, Landay, Long, and Mankoff (2003) describe the drawbacks of sketch recognizers at this time.…”

mentioning

confidence: 99%

A new paradigm based on agents applied to free-hand sketch recognition

Fernández-Pacheco

Albert

Conesa

2012

Expert Systems with Applications

View full text Add to dashboard Cite

devices that allow facing up to the conceptual design phase of a product. Recognizers play an important role in this field, allowing the interpretation of the user's intention, but they still present some important lacks. This paper proposes a new recognition paradigm using an agentbased architecture that does not depend on the drawing sequence and takes context information into account to help decisions. Another improvement is the absence of operation modes, that is, no button is needed to distinguish geometry from symbols or gestures, and also "interspersing"and "overtracing" are accomplished.

show abstract

An Agent-Based Multimodal Interface for Sketch Interpretation

Cited by 14 publications

References 9 publications

An agent-based framework for sketched symbol interpretation

An agent-based framework for sketched symbol interpretation

An Agent-Based Paradigm for Free-Hand Sketch Recognition

A new paradigm based on agents applied to free-hand sketch recognition

Contact Info

Product

Resources

About