Demonstration of the approach presented on the paper entitled Ensembling Shallow Siamese Neural Network Architectures for Printed Documents Verification in Data-Scarcity Scenarios, published at IEEE Access in 2021.

You can find the paper HERE

There is a python notebook (Demo_Snn.ipynb) that you can run and see the source code working in some example images.

We could not upload the data and models due to Github's space limitations. So you need to download them from https://drive.google.com/drive/folders/1WBHWhnZ_tX7P3dhrSYwXc4tqybtJ8_vH?usp=sharing

Once downloaded, join the subfolders together with the github repository you just cloned.

Any suggestions and issues found in the code or in the downloading/configuration steps can be reported to anselmo.ferreira "at" gmail.com