Writer identification using edge-based directional features

Abstract

This paper evaluates the performance of edge-based directionalprobability distributions as features in writer identificationin comparison to a number of non-angular features.It is noted that the joint probability distribution of theangle combination of two "hinged" edge fragments outperformsall other individual features. Combining features mayimprove the performance. Limitations of the method pertainto the amount of handwritten material needed in orderto obtain reliable distribution estimates. The global featurestreated in this study are sensitive to major style variation(upper- vs lower case), slant, and forged styles, whichnecessitates the use of other features in realistic forensicwriter identification procedures.