On assessing the robustness of Pen Coordinates, Pen Pressure and Pen Inclination to Short-term and Long-term Time Variability with Personal Entropy
File is not available to download! Source: IEEE 3rd International Conference on Biometrics : Theory, Applications and Systems (BTAS '09), IEEE, 28-30, Washington, United States, 2009 Authors: N. Houmani, S. Garcia-Salicetti, B. Dorizzi Keywords: Abstract: In this work, we study different combinations of
the five time functions captured by a digitizer in presence or not
of time variability. To this end, we propose two criteria
independent of the classification step: Personal Entropy,
introduced in our previous works and intra-class variability
measure based on Dynamic Time Warping. We confront both
criteria to system performance using an HMM and a DTW
classifiers. Moreover, we introduce the concept of short-term
time variability, proposed on MCYT-100, and long-term time
variability studied with BIOMET database. Our experiments
clarify conflicting results in the literature and confirm some
others: pen inclination angles are very unstable in presence or
not of time variability; the only combination which is robust is
that containing only coordinates; finally, pen pressure is not
recommended in the long-term context, although it may give
better results in terms of performance (according to the classifier
used) in the short-term context. |