Autor(es)

Florencia Iglesias and Pablo Negri and Marıa Elena Buemi and Daniel Acevedo and Marta Mejail

URL Pública

Abstract

The identification of facial expressions with human emotions plays a key role in non-verbal human communication and has applications in several areas. In this work, we analyze two approaches for expression recognition. One of them is a static-based appearance method. In this approach, a binary-based descriptor, denominated Oriented Fast and Rotated BRIEF (ORB), is used on a single frame of a sequence of images to extract texture information, and classified with a Support Vector Machine. The other is a dynamic approach introducing a new simple descriptor based on the angles formed by the landmarks to capture the dynamic of the gesture on an image sequence. In this case the recognition is performed by a Conditional Random Field (CRF) classifier. The paper compares both methodologies, analyze their similarities and differences.