Documents Counterfeit Detection Through a Deep Learning Approach

The main topic of this work is on the detection of counterfeit documents and especially banknotes. We propose an end-to-end learning model using a deep learning approach based on Adapnet++ which manages feature extraction at multiple scale levels using several residual units. Unlike previous models based on regions of interest (ROI) and high-resolution documents, our network is feed with simple input images (i.e., a single patch) and we do not need high resolution images. Besides, discriminative regions can be visualized at different scales. Our network learns by itself which regions of interest predict the better results. Experimental results show that we are competitive compared with the state-of-the-art and our deep neural network has good ability to generalize and can be applied to other kind of documents like identity or administrative one.

[1]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[2]  Allah Bux Sargano,et al.  Android-Based Verification System for Banknotes , 2017, J. Imaging.

[3]  Min-Jen Tsai,et al.  Deep learning for printed document source identification , 2019, Signal Process. Image Commun..

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Mickaël Coustaty,et al.  Local Binary Patterns for Document Forgery Detection , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[6]  John W Bond,et al.  Identification of forged Bank of England £20 banknotes using IR spectroscopy. , 2014, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[7]  Mohamed Deriche,et al.  A bibliography of pixel-based blind image forgery detection techniques , 2015, Signal Process. Image Commun..

[8]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[9]  Oriol Ramos Terrades,et al.  Evaluation of Texture Descriptors for Validation of Counterfeit Documents , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[10]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[11]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[12]  Faisal Shafait,et al.  Printer Identification Using Supervised Learning for Document Forgery Detection , 2014, 2014 11th IAPR International Workshop on Document Analysis Systems.

[13]  Oriol Ramos Terrades,et al.  Recurrent Comparator with Attention Models to Detect Counterfeit Documents , 2019, ICDAR.

[14]  Volker Lohweg,et al.  Banknote authentication with mobile devices , 2013, Electronic Imaging.

[15]  Luc Patiny,et al.  Development of a systematic computer vision-based method to analyse and compare images of false identity documents for forensic intelligence purposes-Part I: Acquisition, calibration and validation issues. , 2016, Forensic science international.

[16]  Josep Lladós,et al.  Banknote Counterfeit Detection through Background Texture Printing Analysis , 2016, 2016 12th IAPR Workshop on Document Analysis Systems (DAS).

[17]  Antoine Doucet,et al.  Find it! Fraud Detection Contest Report , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[18]  Rob Fergus,et al.  Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[19]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[20]  Chulhee Lee,et al.  Detection of counterfeit banknotes using multispectral images , 2018, Digit. Signal Process..

[21]  Carlos Roberto Appoloni,et al.  Characterization of Brazilian banknotes using portable X-ray fluorescence and Raman spectroscopy. , 2019, Forensic science international.

[22]  Ching Yee Suen,et al.  Modified HOG Descriptor-Based Banknote Recognition System , 2018 .

[23]  Claude Roux,et al.  Image processing of false identity documents for forensic intelligence. , 2016, Forensic science international.

[24]  Thomas M. Breuel,et al.  Using DCT Features for Printing Technique and Copy Detection , 2009, IFIP Int. Conf. Digital Forensics.

[25]  Wolfram Burgard,et al.  Self-Supervised Model Adaptation for Multimodal Semantic Segmentation , 2018, International Journal of Computer Vision.