23. Using Entropy to Distinguish Shape versus Text in Hand-Drawn Diagrams
Jun 20, 2009 3623 views 
Most sketch recognition systems are accurate in recognizing either text or shape (graphic) ink strokes,but not both. Distinguishing between shape and text strokes is, therefore, a critical task in recognizing hand-drawn digital ink diagrams that contain text labels and annotations. We have found the entropy rate to be an accurate criterion of classification. We found that the entropy rate is significantly higher for text strokes compared to shape strokes and can serve as a distinguishing factor between the two. The paper has been accepted for publication in the 2009 IJCAI proceedings. This video shows our system in action. Please visit our lab here -> [[http://srlweb.cs.tamu.edu/srlng/home]].