A Face Emotion Recognition Method Using Convolutional Neural Network and Image Edge Computing

Hongli Zhang, Alireza Jolfaei, Mamoun Alazab

Research output: Contribution to journalArticleResearchpeer-review

Abstract

To avoid the complex process of explicit feature extraction in traditional facial expression recognition, a face expression recognition method based on a convolutional neural network (CNN) and an image edge detection is proposed. Firstly, the facial expression image is normalized, and the edge of each layer of the image is extracted in the convolution process. The extracted edge information is superimposed on each feature image to preserve the edge structure information of the texture image. Then, the dimensionality reduction of the extracted implicit features is processed by the maximum pooling method. Finally, the expression of the test sample image is classified and recognized by using a Softmax classifier. To verify the robustness of this method for facial expression recognition under a complex background, a simulation experiment is designed by scientifically mixing the Fer-2013 facial expression database with the LFW data set. The experimental results show that the proposed algorithm can achieve an average recognition rate of 88.56% with fewer iterations, and the training speed on the training set is about 1.5 times faster than that on the contrast algorithm.
Original languageEnglish
Article number08884205
Pages (from-to)159081-159089
Number of pages9
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 28 Oct 2019

Fingerprint

Face recognition
Neural networks
Edge detection
Convolution
Feature extraction
Classifiers
Textures
Experiments

Cite this

@article{e755d357a7ab407f87dc15a708768222,
title = "A Face Emotion Recognition Method Using Convolutional Neural Network and Image Edge Computing",
abstract = "To avoid the complex process of explicit feature extraction in traditional facial expression recognition, a face expression recognition method based on a convolutional neural network (CNN) and an image edge detection is proposed. Firstly, the facial expression image is normalized, and the edge of each layer of the image is extracted in the convolution process. The extracted edge information is superimposed on each feature image to preserve the edge structure information of the texture image. Then, the dimensionality reduction of the extracted implicit features is processed by the maximum pooling method. Finally, the expression of the test sample image is classified and recognized by using a Softmax classifier. To verify the robustness of this method for facial expression recognition under a complex background, a simulation experiment is designed by scientifically mixing the Fer-2013 facial expression database with the LFW data set. The experimental results show that the proposed algorithm can achieve an average recognition rate of 88.56{\%} with fewer iterations, and the training speed on the training set is about 1.5 times faster than that on the contrast algorithm.",
author = "Hongli Zhang and Alireza Jolfaei and Mamoun Alazab",
year = "2019",
month = "10",
day = "28",
doi = "10.1109/ACCESS.2019.2949741",
language = "English",
volume = "7",
pages = "159081--159089",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",

}

A Face Emotion Recognition Method Using Convolutional Neural Network and Image Edge Computing. / Zhang, Hongli; Jolfaei, Alireza; Alazab, Mamoun.

In: IEEE Access, Vol. 7, 08884205, 28.10.2019, p. 159081-159089.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A Face Emotion Recognition Method Using Convolutional Neural Network and Image Edge Computing

AU - Zhang, Hongli

AU - Jolfaei, Alireza

AU - Alazab, Mamoun

PY - 2019/10/28

Y1 - 2019/10/28

N2 - To avoid the complex process of explicit feature extraction in traditional facial expression recognition, a face expression recognition method based on a convolutional neural network (CNN) and an image edge detection is proposed. Firstly, the facial expression image is normalized, and the edge of each layer of the image is extracted in the convolution process. The extracted edge information is superimposed on each feature image to preserve the edge structure information of the texture image. Then, the dimensionality reduction of the extracted implicit features is processed by the maximum pooling method. Finally, the expression of the test sample image is classified and recognized by using a Softmax classifier. To verify the robustness of this method for facial expression recognition under a complex background, a simulation experiment is designed by scientifically mixing the Fer-2013 facial expression database with the LFW data set. The experimental results show that the proposed algorithm can achieve an average recognition rate of 88.56% with fewer iterations, and the training speed on the training set is about 1.5 times faster than that on the contrast algorithm.

AB - To avoid the complex process of explicit feature extraction in traditional facial expression recognition, a face expression recognition method based on a convolutional neural network (CNN) and an image edge detection is proposed. Firstly, the facial expression image is normalized, and the edge of each layer of the image is extracted in the convolution process. The extracted edge information is superimposed on each feature image to preserve the edge structure information of the texture image. Then, the dimensionality reduction of the extracted implicit features is processed by the maximum pooling method. Finally, the expression of the test sample image is classified and recognized by using a Softmax classifier. To verify the robustness of this method for facial expression recognition under a complex background, a simulation experiment is designed by scientifically mixing the Fer-2013 facial expression database with the LFW data set. The experimental results show that the proposed algorithm can achieve an average recognition rate of 88.56% with fewer iterations, and the training speed on the training set is about 1.5 times faster than that on the contrast algorithm.

U2 - 10.1109/ACCESS.2019.2949741

DO - 10.1109/ACCESS.2019.2949741

M3 - Article

VL - 7

SP - 159081

EP - 159089

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 08884205

ER -