Ink features for diagram recognition

Rachel Patel, Beryl Plimmer, John Grundy, Ross Ihaka

Research output: Contribution to conferencePaperpeer-review

26 Citations (Scopus)


The ability to automatically recognize a sketch accurately is important to computer-based diagramming. Many recognition techniques have been proposed but few researchers have reported the use of formal methods to select the most appropriate ink features for recognition algorithms. We have used a statistical approach to identify the most important distinguishing features of ink for dividing text and shapes. We implemented these into an existing recognition engine and conducted a comparative evaluation. Our feature set more successfully classified a range of common diagram elements than two existing dividers.

Original languageEnglish
Number of pages8
Publication statusPublished - 1 Dec 2007
Externally publishedYes
EventSketch-Based Interfaces and Modeling 2007 - ACM SIGGRAPH/Eurographics Symposium - Riverside, CA, United States of America
Duration: 2 Aug 20073 Aug 2007


ConferenceSketch-Based Interfaces and Modeling 2007 - ACM SIGGRAPH/Eurographics Symposium
Country/TerritoryUnited States of America
CityRiverside, CA

Cite this