PT Unknown AU Albert Berenguel Oriol Ramos Terrades Josep Llados Cristina Cañero TI Recurrent Comparator with attention models to detect counterfeit documents BT 15th International Conference on Document Analysis and Recognition PY 2019 DI 10.1109/ICDAR.2019.00215 AB 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. ER