Skip to main content
. Author manuscript; available in PMC: 2013 Aug 13.
Published in final edited form as: J Mach Learn Res. 2012 May 1;13:1589–1608.

Figure 6.

Figure 6

Shown in the above are the six feature spaces defining each of the six basic emotion categories. A simple linear Support Vector Machine (SVM) can achieve high classifica-tion accuracies; where we have used a one-versus-all strategy to construct each classifier and tested it using the leave-one-out strategy. Here, we only used two features (dimensions) for clarity of presentation. Higher accuracies are obtained if we include additional dimensions and training samples.