PT Unknown
AU Albert Berenguel
   Oriol Ramos Terrades
   Josep Llados
   Cristina Cañero
TI Evaluation of Texture Descriptors for Validation of Counterfeit Documents
BT 14th International Conference on Document Analysis and Recognition
PY 2017
BP 1237
EP 1242
DI 10.1109/ICDAR.2017.204
AB This paper describes an exhaustive comparative analysis and evaluation of different existing texture descriptor algorithms to differentiate between genuine and counterfeit documents. We include in our experiments different categories of algorithms and compare them in different scenarios with several counterfeit datasets, comprising banknotes and identity documents. Computational time in the extraction of each descriptor is important because the final objective is to use it in a real industrial scenario. HoG and CNN based descriptors stands out statistically over the rest in terms of the F1-score/time ratio performance.
ER