RT info:eu-repo/semantics/article
T1 Using the score ratio with distance-based classifiers: A theoretical and practical study in biometric signature recognition
A1 Vivaracho-Pascual, Carlos
A1 Simon-Hurtado, Arancha
A1 Manso-Martinez, Esperanza
K1 Score ratio, Signature verification, Distance-based classifier
AB The binary classification problem where an input is classified as belonging or not to a certain class, the so-called Target Class (TC), is approached here. This problem can be stated as a basic hypothesis test: X is from the TC (H0) vs. X is not from the TC (H1), where X is the classifier input. When probabilistic models are used (e.g., Hidden Markov Models or Gaussian Mixture Models), the likelihood ratio, p(X/H0)/p(X/H1), is an alternative widely used to improve the classification. However, as far as we know, this ratio is not usually applied with distance-based classifiers (e.g., Dynamic Time Warping). Following that idea, here we propose making the decision based not only on the score (“score” being the classifier output) assuming X to be from the TC (H0), but also using the score assuming X is not from the TC (H1), by means of the ratio between both scores: the score ratio. The proposal is tested in biometric person authentication using manuscript signature, with three different state-of-the-art systems based on distance classifiers. Different alternatives for applying the proposal are shown in order to reduce the computer load, should it prove necessary. Using the score ratio has led to improvements in most of the tests performed. The best verification results were achieved using our proposal, with the best ones without the score ratio being improved by an average of 22%.
PB Elsevier
YR 2017
FD 2017-07-26
LK https://uvadoc.uva.es/handle/10324/64833
UL https://uvadoc.uva.es/handle/10324/64833
LA spa
NO Neurocomputing, Volume 248, Pages 57-66, 26 July, 2017
DS UVaDOC
RD 03-jun-2024