search

taranO / Mobile-authentication-of-CDP

The repository of WIFS 2021 paper: "Mobile authentication of copy detection patterns: how critical is to know fakes?
4 stars 1 forks source link

Missing Files and Wrong Model Input #1

Open Simone-Alghisi opened 1 year ago

Simone-Alghisi commented 1 year ago

I'm Simone Alghisi, a student from the University of Trento. Together with a couple of colleagues, we noticed that there are mainly two problems in the proposed code:

  1. firstly, there is no Classifier.py under the libs folder, meaning that it is not possible to train supervisedly a model;
  2. secondly, the dataset Indigo Mobile has images of 330x330. However, the proposed U-Net implementation accepts images with a size compatible with a power of two, meaning that it is impossible to train a one-class SVM.

Sincerely.

taranO commented 1 year ago

Hello,

First of all, I would like to thanks you for your interest to our work.

  1. The Classifier.py has been added.
  2. To satisfy the U-Net requirement, you can use the central cropping of the appropriate size assuring that the image starts from the fool (non-cropped) symbol at top left.

Best regards.

programatix commented 11 months ago

The lib, libs.to_public.BaseClass is also missing.