Please use this identifier to cite or link to this item:
Title: Physiological inspired neural networks for emotion recognition
Authors: Ferreira, Pedro M.
Marques, Filipe
Cardoso, Jaime S.
Rebelo, Ana
Keywords: Facial expressions recognition
Convolutional neural networks
Issue Date: 2018
Publisher: IEEE
Citation: Ferreira, P. M., Marques, F., Cardoso, J. S., & Rebelo, A. (2018). Physiological inspired neural networks for emotion recognition,, 6, 53930-53943. doi: 10.1109/ACCESS.2018.2870063. Disponível no Repositório UPT,
Abstract: Facial expression recognition (FER) is currently one of the most active research topics due to its wide range of applications in the human-computer interaction field. An important part of the recent success of automatic FER was achieved thanks to the emergence of deep learning approaches. However, training deep networks for FER is still a very challenging task, since most of the available FER data sets are relatively small. Although transfer learning can partially alleviate the issue, the performance of deep models is still below of its full potential as deep features may contain redundant information from the pre-trained domain. Instead, we propose a novel end-to-end neural network architecture along with a well-designed loss function based on the strong prior knowledge that facial expressions are the result of the motions of some facial muscles and components. The loss function is defined to regularize the entire learning process so that the proposed neural network is able to explicitly learn expression-specific features. Experimental results demonstrate the effectiveness of the proposed model in both lab-controlled and wild environments. In particular, the proposed neural network provides quite promising results, outperforming in most cases the current state-of-the-art methods.
ISSN: 2169-3536
Appears in Collections:REMIT – Artigos em Revistas Internacionais / Papers in International Journals

Files in This Item:
File Description SizeFormat 
2018PFerreiraIEEEAccess.pdf2.37 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.