Title: Facial expression recognition based on convolution neural network and orthogonal neighbourhood preserving projection

Authors: Lunzheng Tan; Rui Ding

Addresses: School of Information Engineering, Zhongshan Polytechnic, Zhongshan, Guangdong, 528400, China ' School of Optoelectronic Information, Zhongshan Torch Polytechnic, Zhongshan, Guangdong, 528436, China

Abstract: Aiming at the problems of low recognition rate and poor real-time performance of traditional expression recognition methods, a real-time facial expression recognition model for a convolution neural network (CNN) combined with orthogonal neighbourhood preserving projection (ONPP) is proposed. First, the input image is subjected to a series of pre-processing steps. Then, we use ONPP to reduce the feature dimensions, while preserving global geometry as well as local neighbourhood relationships. Finally, we train and fine-tune the CNN on a massive facial expression database. The method is compared with other mainstream methods on a massive expression database, and experimental results show that the proposed method has higher recognition accuracy and good real-time performance compared to other mainstream methods.

Keywords: facial expression recognition; ONPP; orthogonal neighbourhood preserving projection; CNN; convolution neural network; pre-processing of image.

DOI: 10.1504/IJAACS.2020.110747

International Journal of Autonomous and Adaptive Communications Systems, 2020 Vol.13 No.3, pp.246 - 259

Received: 07 Nov 2019
Accepted: 30 Dec 2019

Published online: 13 Oct 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article