Hybrid Separable Convolutional Inception Residual Network for Human Facial Expression Recognition

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

9 Scopus Citations
View graph of relations

Detail(s)

Original languageEnglish
Title of host publicationProceedings of 2020 International Conference on Machine Learning and Cybernetics
PublisherInstitute of Electrical and Electronics Engineers
Pages21-26
Number of pages6
ISBN (Electronic)978-1-6654-1943-7, 978-0-7381-2426-1
ISBN (Print)978-1-6654-3007-4
Publication statusPublished - Dec 2020

Publication series

NameProceedings - International Conference on Machine Learning and Cybernetics
Volume2020-December
ISSN (Print)2160-133X
ISSN (Electronic)2160-1348

Conference

Title19th International Conference on Machine Learning and Cybernetics (ICMLC 2020)
LocationVirtual
PlaceAustralia
CityAdelaide
Period4 December 2020

Abstract

Facial expression recognition has been applied widely in human-machine interactions, security and business applications. The aim of facial expression recognition is to classify human expressions from their face images. In this work, we propose a novel neural network-based pipeline for facial expression recognition, Hybrid Separable Convolutional Inception Residual Network, using transfer learning with Inception residual network and depth-wise separable convolution. Specifically, our method uses multi-task convolutional neural network for face detection, then modifies the last two blocks of the original Inception residual network using depthwise separable convolution to reduce the computation cost, and finally utilizes transfer learning to take advantages of the transferable weights from a large face recognition dataset. Experimental result on three different databases - the Radboud Faces Database, Compounded Facial Expression of Emotions Database, and Real-word Affective Face Database, shows superior performance compared with the existing studies. Moreover, the proposed method is computationally efficient and reduces the trainable parameters by approximately 25% than the original Inception residual network.

Research Area(s)

  • Facial expression recognition, Inception residual network, Transfer learning, Depthwise separable convolution

Citation Format(s)

Hybrid Separable Convolutional Inception Residual Network for Human Facial Expression Recognition. / FAN, Xinqi; RIZWAN, QURESHI; SHAHID, Ali R. et al.
Proceedings of 2020 International Conference on Machine Learning and Cybernetics. Institute of Electrical and Electronics Engineers, 2020. p. 21-26 9469558 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 2020-December).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review