%0 Conference Proceedings
%T Banknote counterfeit detection through background texture printing analysis
%A Albert Berenguel
%A Oriol Ramos Terrades
%A Josep Llados
%A Cristina Cañero
%B 12th IAPR Workshop on Document Analysis Systems
%D 2016
%F Albert Berenguel2016
%O DAG; 600.061; 601.269; 600.097
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2950), last updated on Thu, 28 Mar 2019 09:42:39 +0100
%X This paper is focused on the detection of counterfeit photocopy banknotes. The main difficulty is to work on a real industrial scenario without any constraint about the acquisition device and with a single image. The main contributions of this paper are twofold: first the adaptation and performance evaluation of existing approaches to classify the genuine and photocopy banknotes using background texture printing analysis, which have not been applied into this context before. Second, a new dataset of Euro banknotes images acquired with several cameras under different luminance conditions to evaluate these methods. Experiments on the proposed algorithms show that mixing SIFT features and sparse coding dictionaries achieves quasi perfect classification using a linear SVM with the created dataset. Approaches using dictionaries to cover all possible texture variations have demonstrated to be robust and outperform the state-of-the-art methods using the proposed benchmark.
%U http://dx.doi.org/10.1109/DAS.2016.34