Title: Multi pose facial expression recognition based on convolutional neural network

Authors: Yongliang Feng

Addresses: School of Information Engineering, Xi'an University, Xi'an 710065, China; Shaanxi Artificial Intelligence Laboratory, Xi'an 710065, China; Xi'an Iot Application Engineering Laboratory, Xi'an 710065, China

Abstract: In order to overcome the problems of low expression similarity and low recognition rate in multi pose facial expression recognition, a new multi pose facial expression recognition method based on convolutional neural network is proposed. The convolution layer is constructed directly by Gabor wavelet with fixed weights, and the full connection layer is constructed by support vector machine (SVM). The structure of convolution neural network is determined by matching growth rules, and the network parameters are trained by back-propagation algorithm. Adaboos algorithm is used to cut facial expression, gradient integral projection and dual threshold binarisation are used to locate eyes. The scale normalisation and grey scale normalisation are used to realise multi pose facial expression recognition. The experimental results show that the highest expression similarity is 98.43%, the recognition rate is close to 100% under different rotation angles, and the recognition rate is as high as 99.96% for different expressions.

Keywords: convolution neural network; multi pose; facial expression; eecognition; Adaboos algorithm.

DOI: 10.1504/IJBM.2022.124670

International Journal of Biometrics, 2022 Vol.14 No.3/4, pp.253 - 267

Received: 13 Jul 2020
Accepted: 08 Sep 2020

Published online: 05 Aug 2022 *

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