Towards Sketch Recognition by Mirroring: Extended Abstract

Humans increasingly use sketches, drawn on paper, on a computer, or via hand gestures in the air, as part of their communications with agents, robots, and other humans. To recognize shapes in sketches, most existing work focuses on offline (post-drawing) recognition methods, trained on large sets of examples . Given the infinite number of ways in which shapes can appear-rotated, scaled, translated-and given inherent inaccuracies in the drawings, these methods do not allow on-line recognition, and require a very large library (or expensive pre-processing) in order to recognize even a small number of shapes. We present an online shape recognizer that identifies multi-stroke geometric shapes without a plan library. Inspired by mirroring processes hypothesized to take place in socially-intelligent brains, the recognizer uses a shape-drawing planner for drawn-shape recognition. It is a form of plan recognition from planning.