| 1. A computer-implemented system that facilitates recognition, comprising:
at least one processor configured to execute the following computer-executable components: a component that receives at least one input containing digital ink strokes;a computer-executable recognition component that identifies and groups at least a subset of the digital ink strokes from the
input into at least one recognized annotation;a computer-executable classification component executing from a computer memory employing at least one type detector that
classifies the recognized annotation into at least one type of a group of extensible types, the at least one type detector
determines a best idealized version of the subset of the digital ink strokes of the at least one recognized annotation determined
according to the at least one type using stroke features that capture similarity of the subset of the digital ink strokes
with an idealized version of an annotation associated with the at least one type detector; a resolution component that facilitates
the recognition of the subset of the digital ink strokes by maximizing a number of explained strokes, maximizing an overall
confidence, and minimizing a number of hypotheses for the input, the resolution component optimizes recognition of the annotation
via employment of an energy function given by:
where α and β are empirically-determined weights.
|
