A Citation k-NN approach for facial expression recognition

NEGRI PABLO; M. MEJAIL; BUEMI, M. E.; ACEVEDO D.; GOMEZ FERNANDEZ, FRANCISCO

Valparaiso

Congreso; 22nd IBEROAMERICAN CONGRESS ON PATTERN RECOGNITION; 2017

Universidad Técnica Federico Santa María, Chile

The identification of facial expressions with human emotions playsa key role in non-verbal human communication and has applications in severalareas. In this work, we propose a descriptor based on areas and angles of trianglesformed by the landmarks from face images. We test this descriptors for facialexpression recognition by means of an adaptation of the k-Nearest Neighborsclassifier called Citation-kNN in which the training examples come in the formof sets of feature vectors. Comparisons with other state-of-the-art techniques onthe CK+ dataset are shown. The descriptor remains robust and precise in therecognition of expressions.