The SiGeR (Simple Gesture Recogniser) algorithm was developed by Scott Swigart for the Microsoft Developer Network to illustrate the implementation of custom gesture recognisers for the Microsoft Tablet PC platform. The algorithm classifies gestures on the basis of regular expressions.
Gestures are described with the eight cardinal points (N, NE, E, SE, S, SW, W and NW) and some statistical information. Out of this description a regular expression is created. These regular expressions are applied to input gestures and if a class description matches the input string, the gesture class is recognised as result. Therefore the classification is binary and it is not possible to rate different results.
For example the gesture shown in Figure 4.1, starting at the red dot, can be described with the following character string: E, N, W, S. Out of these characters the regular expression (E)+(N)+(W)+(S)+ can be created. Because hand drawn lines may not be always straight, the author proposed a more general form of the regular expression which also accepts neighbouring distances. So the extended regular expression for this example gesture would be (NE|E|SE)+(NW|N|NE)+(SW|W|NW)+(SE|S|SW)+.
|MIN_DISTANCE||The minimal distance denotes the minimal space between two succeeding points of a gesture. Succeeding points which are too close may have a negative influence for the computation of particular features and are not meaningful in the context of the entire gesture.|