Through the following link, we provide the table of results mentioned in the paper.
Through the following link, we provide the raw results for all combinations of features, classifiers, and training protocol as well as for all metrics (available as a Python dictionary). Each key of the dictionary is in the form (protocol, classifier, feature, metric). The value of each corresponding key represents the accuracy for the corresponding metric.
As kindly noticed by a student from the Friedrich-Alexander-Universität, the link we have provided on the paper to a dataset from previous work is now invalid. What we have employed on our work was, in fact, the features vectors previously employed by [2].
| [1] | Mendes Júnior, Pedro; Bondi, Luca; Bestagini, Paolo; Tubaro, Stefano; Rocha, Anderson (2019), “An in-depth study on open-set camera model identification”, IEEE Access. 7:180713–180726. BibTeX |
| [2] | Bondi, Luca; Luca, Baroffio; David, Güera; Bestagini, Paolo; Edward J., Delp; Tubaro, Stefano (2017), “First Steps Toward Camera Model Identification with Convolutional Neural Networks”, IEEE Signal Processing Letters. 24(3):259–263. |