Caracterización de unidades de acción facial combinando métodos kernel y análisis de componentes independientes

the facial expressions give crucial information about the behavior of human emotion to study, cognitive processes, and social interaction. the work described in this paper presents a methodology for characterizing facial action units (aus), which represents the subtle change of facial expressions, based on kernels methods perform a nonlinear maping of data and looking for directions to the projections of the data in feature space through independent component analysis (ica). the methodology validation was done on cohn-kande database. image preprocessing was done through histogram equalization, a whitening on data with kernel principal component analysis (kpca), for that the mapped in feature space search a lineal structure of the input data, finally we applied ica for make the projected distribution of data is at least possible gaussian. the results were 96.64% accuracy for average recognition of three combinations of facial aus of the whole face more neutral faces, was detected mainly changes that occur between rapid transitions of aus are shown instantly. although the results don't exceed the best rate reported in the current state of the art which are of the order 97% accuracy, if they are very approximate, additionally the proposed methodology can reduce the size of the feature space because they represent the data only in terms of independent components, so as to use only those variables that provided greater information, which reduce the complexity of the classifier.