The effect of task on classification accuracy: using gesture recognition techniques in free-sketch recognition

Generating, grouping, and labeling free-sketch data is a difficult and time-consuming task for both user study participants and researchers. To simplify this process for both parties, we would like to have users draw isolated shapes instead of complete sketches that must be hand-labeled and grouped, and then use this data to train our free-sketch symbol recognizer. However, it is an open question whether shapes draw in isolation accurately reflect the way users draw shapes in a complete diagram. Furthermore, many of the simplest shape recognition algorithms were designed to recognize gestures, and it is not clear that they will generalize to freely-drawn shapes. To answer these questions, we perform experiments using three different recognizers to measure the effect of the data collection task on recognition accuracy. We find that recognizers trained only on isolated shapes can classify freely-sketched shapes as well as the same recognizers trained on free-sketches. We also show that user-specific training examples significantly improve recognition rates. Finally, we introduce a variant of a popular and simple gesture recognition algorithm that recognizes freely-drawn shapes as well as a highly-accurate but more complex recognizer designed explicitly for free-sketch recognition.