Open Access

Table E.1

Classification results for the SVM+PSF classifier.

Model F1 Accuracy Top-two accuracy
PCA+MLP 0.366 0.370 0.757
CNN+MLP 0.385 0.391 0.746

SVM+PSFS1${\rm{SVM}} + {\rm{PS}}{{\rm{F}}_{{{\cal S}_1}}}$ 0.392 0.410 0.755
SVM+PSFS2${\rm{SVM}} + {\rm{PS}}{{\rm{F}}_{{{\cal S}_2}}}$ 0.431 0.450 0.816
SVM+PSFS3${\rm{SVM}} + {\rm{PS}}{{\rm{F}}_{{{\cal S}_3}}}$ 0.491 0.498 0.869
SVM+PSFS4${\rm{SVM}} + {\rm{PS}}{{\rm{F}}_{{{\cal S}_4}}}$ 0.506 0.512 0.873
SVM+PSFS5${\rm{SVM}} + {\rm{PS}}{{\rm{F}}_{{{\cal S}_5}}}$ 0.516 0.525 0.884
SVM+PSFS6${\rm{SVM}} + {\rm{PS}}{{\rm{F}}_{{{\cal S}_6}}}$ 0.523 0.529 0.886
SVM+PSFGT 0.546 0.549 0.910

Notes: Each row shows a different PSF model used for computing the similarity features. The pixel-only classification metrics correspond to the first two rows.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.