Experimental evaluation of an on-line scribble recognizer

We present a fast, simple and compact approach to recognize Scribbles (multi-stroke geometric shapes) drawn with a stylus on a digitizing tablet. Our method is able to identify shapes of different sizes and rotated at arbitrary angles, drawn with dashed, continuous strokes or overlapping lines. We use temporal adjacency to allow users to input the most common shapes in drawing such as triangles, lines, rectangles, circles, diamonds and ellipses, using multiple strokes. We have further extended this approach to identify useful shapes such as arrows, crossing lines and uni-stroke gestural commands and have developed a library of software components to make this software generally available. The recognition algorithm uses Fuzzy Logic and geometric features, combined with an extensible set of heuristics to classify scribbles. Most recent evaluation results show recognition rates over 97%.