Facial expression analysis by generalized eigen-space method based on class-features (GEMC)

Abstract

This paper describes a new method of facial expression recognition based on Independent Component Analysis (ICA) and eigen-space method. We had proposed Eigen-space Method based on Class-features (EMC), and EMC was the outstanding method with classification accuracy superior to Multiple Discriminant Analysis (MDA). Our new method, GEMC, is a generalization of EMC by using ICA technique. GEMC has discriminated the facial expression class in a precision 10 or more points higher than conventional methods (EMC, MDA and ICA) because of classification experiments.

Facial action units detection by robust temporal features

“…The bar graph shows the average accuracy of each single action unit detectors. In our evaluation, the previous architecture of EMC [21] and ICA with whitened EMC [17] are applied as the baseline methods. The new architecture of subspace methods derived by multiple binary classifiers are denoted by M-ICA and M-EMC respectively (see numerical details in Table.…”

“…However, the original ICA was not designed for the class separation problem. Therefore, we adopt the idea of class separation by ICA with whitened EMC in [17] due to its superiority in class separation over other discriminant analysis methods.…”

“…4. [21] and discriminative ICA in [17]. The performances of all action unit detectors are evaluated by randomly spiting training and testing set (see details of M-EMC and M-ICA in Table.II)…”