Affiliations: [a] Laboratoire Signaux et Images, Université des Sciences et de la Technologie d’Oran Mohamed Boudiaf, USTO-MB, BP1505, El M’naouer, Oran, Algeria | [b] Dpto. de Inteligencia Artificial, Universidad Nacional de Educación a Distancia, Madrid, Spain | [c] Dpto. Tecnologías de la Información y las Comunicaciones, University Politécnica de Cartagena, Cartagena, Spain | [d] Dpto. Electrónica, Tecnología de Computadoras y Proyectos, University Politécnica de Cartagena, Cartagena, Spain | [e] Instituto de Bioingeniería, University Miguel Hernández, Elche, Spain
Correspondence:
[*]
Corresponding author: Jose Manuel Ferrández-Vicente, Dpto. Tecnologías de la Información y las Comunicaciones, University Politécnica de Cartagena, Cartagena, Spain. E-mail: [email protected].
Abstract: Facial emotion recognition (FER) has been extensively researched over the past two decades due to its direct impact in the computer vision and affective robotics fields. However, the available datasets to train these models include often miss-labelled data due to the labellers bias that drives the model to learn incorrect features. In this paper, a facial emotion recognition system is proposed, addressing automatic face detection and facial expression recognition separately, the latter is performed by a set of only four deep convolutional neural network respect to an ensembling approach, while a label smoothing technique is applied to deal with the miss-labelled training data. The proposed system takes only 13.48 ms using a dedicated graphics processing unit (GPU) and 141.97 ms using a CPU to recognize facial emotions and reaches the current state-of-the-art performances regarding the challenging databases, FER2013, SFEW 2.0, and ExpW, giving recognition accuracies of 72.72%, 51.97%, and 71.82% respectively.
