Automatic interpretation of depiction conventions in sketched diagrams

Authors:
Kate Lockwood;Andrew Lovett;Ken Forbus;Morteza Dehghani;Jeff Usher
Affiliations:
Qualitative Reasoning Group, Northwestern University, Evanston, IL;Qualitative Reasoning Group, Northwestern University, Evanston, IL;Qualitative Reasoning Group, Northwestern University, Evanston, IL;Qualitative Reasoning Group, Northwestern University, Evanston, IL;Qualitative Reasoning Group, Northwestern University, Evanston, IL
Venue:
SBM'08 Proceedings of the Fifth Eurographics conference on Sketch-Based Interfaces and Modeling
Year:
2008

Citing 8
Cited 0

A logical framework for depiction and image interpretation

Artificial Intelligence
Understanding Diagrams in Technical Documents

Computer
Towards a computational model of sketching

Proceedings of the 6th international conference on Intelligent user interfaces
DiaSketches

Proceedings of the 2nd international symposium on Smart graphics
Calculi for Qualitative Spatial Reasoning

AISMC-3 Proceedings of the International Conference AISMC-3 on Artificial Intelligence and Symbolic Mathematical Computation
Finding Perceptually Closed Paths in Sketches and Drawings

IEEE Transactions on Pattern Analysis and Machine Intelligence
Hierarchical parsing and recognition of hand-sketched diagrams

Proceedings of the 17th annual ACM symposium on User interface software and technology
SketchREAD: a multi-domain sketch recognition engine

Proceedings of the 17th annual ACM symposium on User interface software and technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Diagrams are used in many educational settings to convey physical and spatial information. Sketching is used, in turn, to test students' understanding of course concepts. The availability of Tablet PCs offer an exciting opportunity to create intelligent tutoring systems which automatically provide students with feedback on sketched work, and to create systems which can capture knowledge via interaction with people. However, for such systems to provide useful and relevant feedback, the software must be able to interpret diagrams that students have drawn. Interpreting diagrams correctly requires an understanding of some basic depiction conventions common in diagrammatic representation. Here we describe how to combine general semantic information about objects in sketched diagrams with geometric information from the sketch to aid in the interpretation of regions and edges. This system is implemented as an extension to the CogSketch sketch understanding system.