alvarado-UIST2004 - SketchREAD A Multi-Domain Sketch...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
SketchREAD: A Multi-Domain Sketch Recognition Engine Christine Alvarado MIT CSAIL Cambridge, MA 02139 USA [email protected] Randall Davis MIT CSAIL Cambridge, MA 02139 USA [email protected] ABSTRACT We present SketchREAD, a multi-domain sketch recognition engine capable of recognizing freely hand-drawn diagram- matic sketches. Current computer sketch recognition systems are difficult to construct, and either are fragile or accomplish robustness by severely limiting the designer’s drawing free- dom. Our system can be applied to a variety of domains by providing structural descriptions of the shapes in that do- main; no training data or programming is necessary. Robust- ness to the ambiguity and uncertainty inherent in complex, freely-drawn sketches is achieved through the use of con- text. The system uses context to guide the search for possible interpretations and uses a novel form of dynamically con- structed Bayesian networks to evaluate these interpretations. This process allows the system to recover from low-level recognition errors (e.g., a line misclassified as an arc) that would otherwise result in domain level recognition errors. We evaluated SketchREAD on real sketches in two domains— family trees and circuit diagrams—and found that in both do- mains the use of context to reclassify low-level shapes signif- icantly reduced recognition error over a baseline system that did not reinterpret low-level classifications. We also discuss the system’s potential role in sketch-based user interfaces. Categories and Subject Descriptors: I.5.4 [ Pattern Recog- nition ]: Applications; H.5.2 [ User Interfaces ]: Interaction Styles Additional Keywords and Phrases: Pen-based UIs, in- put and interaction technology, sketch recognition, intelligent UIs, Bayesian networks 1 INTRODUCTION While in recent years there has been an increasing interest in sketch-based user interfaces [9, 13, 14], the problem of robust free-sketch recognition remains largely unsolved. Be- cause existing sketch recognition techniques are difficult to implement, and are error-prone or severely limit the user’s drawing style, many previous systems that support sketching perform only limited recognition. ScanScribe, for example, uses perceptual guidelines to support image and text editing, but does not attempt to recognize the user’s drawing [14]. Similarly, the sketch-based DENIM system supports the de- Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. UIST ’04
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 06/12/2011 for the course CAP 6105 taught by Professor Lavoila during the Spring '09 term at University of Central Florida.

Page1 / 10

alvarado-UIST2004 - SketchREAD A Multi-Domain Sketch...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online