%0 Conference Proceedings
%T Recurrent Comparator with attention models to detect counterfeit documents
%A Albert Berenguel
%A Oriol Ramos Terrades
%A Josep Llados
%A Cristina Cañero
%B 15th International Conference on Document Analysis and Recognition
%D 2019
%F Albert Berenguel2019
%O DAG; 600.140; 600.121; 601.269
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3456), last updated on Tue, 23 Nov 2021 15:20:38 +0100
%X This paper is focused on the detection of counterfeit documents via the recurrent comparison of the security textured background regions of two images. The main contributions are twofold: first we apply and adapt a recurrent comparator architecture with attention mechanism to the counterfeit detection task, which constructs a representation of the background regions by recurrently condition the next observation, learning the difference between genuine and counterfeit images through iterative glimpses. Second we propose a new counterfeit document dataset to ensure the generalization of the learned model towards the detection of the lack of resolution during the counterfeit manufacturing. The presented network, outperforms state-of-the-art classification approaches for counterfeit detection as demonstrated in the evaluation.
%U https://ieeexplore.ieee.org/document/8977990
%U http://dx.doi.org/10.1109/ICDAR.2019.00215