Fig. 17

The third scenario results’ visualization: a the distribution of (i) the symbol-wise Hamming distance between the digital templates and its corresponding estimations via the encoder model trained with respect to the \(\mathcal {D}_{{\textrm{t}} \hat{\textrm{t}}}\) term and (ii) the \(\ell _2\) distance between the printed codes and its corresponding reconstructions by the decoder model trained with respect to the \(\mathcal {D}_{{\textrm{x}} \hat{\textrm{x}}}\) term; b the OC-SVM decision boundaries