On measuring forgery quality in online signatures

This work proposes a novel measure to quantify the quality of a skilled forgery sample in the online signature framework. Such a quality measure is constructed by adapting our former Personal Entropy to the context of skilled forgeries production. For validation, we confront our quality measure to several types of skilled forgeries (static, dynamic, professional) captured on different acquisition platforms. Indeed, four databases are exploited: MCYT-100, Philips database, BioSecure data subsets DS2 and DS3. We prove the effectiveness of our quality measure to quantify the quality of all types of skilled forgeries available with regards to the performance of three classifiers: a Dynamic Time Warping, a Hidden Markov models and a Gaussian Mixture Model.

► Proposing a novel quality measure quantifying the quality of a skilled forgery sample.
► Labeling skilled forgery samples according to their quality by Hierarchical Clustering.
► Assessing the impact of dynamic vs. static parameters on our forgery quality measure.
► Assessing performance on forgery quality categories with 3 classifiers.