patel - Exploring Better Techniques for Diagram Recognition...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Exploring Better Techniques for Diagram Recognition Rachel Patel 1 , Beryl Plimmer 1 , John Grundy 1, 2 , Ross Ihaka 3 1 Department of Computer Science 2 Department of Electrical and Computer Engineering 3 Department of Statistics University of Auckland Private Bag 92019, Auckland, New Zealand {rpat088@ec, beryl@cs, john-g@cs, ihaka@stat}.auckland.ac.nz Abstract. A critical component of diagramming sketch tools is their ability to reliably recognise hand-drawn diagram components. This is made difficult by the presence of both geometric shapes and characters in diagrams. The goal of our research is to improve sketch recognition by improving the accuracy in grouping and classifying strokes in a diagram into text characters and shapes. We have done this by identifying the most significant features of strokes that can be used to distinguish shapes from text using a decision tree based parti- tioning technique. Implementation and evaluation of this new “shape divider” using these features against InkKit’s existing divider and the Microsoft divider has shown that our divider is more accurate at dividing text and shape strokes and can therefore improve overall sketch recognition. Keywords: Human Computer Interaction, Pattern Recognition 1. Introduction Computers can be used to produce formal diagrams e.g. software designs, user inter- face designs, CAD specifications, hierarchy charts and so on. However, in the begin- ning of a project it can be better to use pen and paper. The reason is that these simple, human-centric design tools are far more flexible which encourages creativity and in turn this produces better designs in the end. However a computer offers easy editing and distribution features and greater formality to the look of a diagram and so some- times the important pen and paper design stage is overlooked. Imagine being able to sketch diagrams directly onto a computer screen and have them accurately translated into formalized representations. The Tablet PC supports sketching of characters and recognition of these but has much weaker support for general diagram drawing and accurate recognition . InkKit [8] is a sketch tool for the Tablet PC that has been designed to bridge the gap between pen and paper and com- puters. InkKit allows you to sketch any type of diagram using the Tablet PC’s stylus. Its recognition engine then identifies each component of the diagram and transforms it into a formal, tidy version in a specified format such as HTML or a Word drawing ob- ject. InkKit has been used as a foundation for this research.
Background image of page 1

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

View Full DocumentRight Arrow Icon
2. Motivation A critical part of diagramming sketch tools is being able to reliably recognise the hand-drawn diagram components. The purpose of this Masters project is
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 8

patel - Exploring Better Techniques for Diagram Recognition...

This preview shows document pages 1 - 3. Sign up to view the full document.

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