Summary
In this paper entropy rates are proposed as a discriminator between text and shape. Since text strokes usually show more curvature change, the authors have utilized this to distinguish them from other shapes.
Their accuracy of classification reached around 92% which is fine for a relatively simple method.
Discussion
It is a more decent an different approach than the decision tree which was discussed in previous papers.
The accuracy rates for text was close to 98% when the system was only allowed to be non-committal on 10% (or less) of the strokes.
ReplyDelete