Understanding Abstraction in Deep CNN: An Application on Facial Emotion Recognition

Francesca Nonis , Pietro Barbiero (1) , Giansalvo Cirrincione (2) , Elena Carlotta Olivetti , Federica Marcolin (3) , Enrico Vezzetti

1 CAM - University of Cambridge [UK]
2 LTI - Laboratoire des technologies innovantes - UR UPJV 3899
3 DIGEP - Department of Management and Production Engineering [Politecnico di Torino]

Facial Emotion Recognition (FER) is the automatic processing of human emotions by means of facial expression analysis [1]. The most common approach exploits 3D Face Descriptors (3D-FD) [2], which derive from depth maps [3] by using mathematical operators. In recent years, Convolutional Neural Networks (CNNs) have been successfully employed in a wide range of tasks including large-scale image classification systems and to overcome the hurdles in facial expression classification. Based on previous studies, the purpose of the present work is to analyze and compare the abstraction level of 3D face descriptors with abstraction in deep CNNs. Experimental results suggest that 3D face descriptors have an abstraction level comparable with the features extracted in the fourth layer of CNN, the layer of the network having the highest correlations with emotions.

Domaines: Informatique [cs]

Francesca Nonis, Pietro Barbiero, Giansalvo Cirrincione, Elena Carlotta Olivetti, Federica Marcolin, et al.. Understanding Abstraction in Deep CNN: An Application on Facial Emotion Recognition. Progresses in Artificial Intelligence and Neural Systems, 184, Springer Singapore, pp.281-290, 2021, Smart Innovation, Systems and Technologies, ⟨10.1007/978-981-15-5093-5_26⟩. ⟨hal-03845694⟩