Abstract  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. Using a single feature – zero-order entropy  rate – our system produced a correct classification  rate of 92.06% on test data belonging to diagrammatic domain for which the threshold was trained  on. It also performed favorably on an unseen domain for which no training examples were supplied