A facial expression recognition method based on face texture feature fusion
Aiming at facial expression recognition, the recognition rate is not high due to noise and occlusion. A hybrid approach of facial expression has been presented by combining local and global features. First, feature extraction is performed to fuse the histogram of oriented gradients (HOG) descriptor...
Guardado en:
Autores principales: | , , |
---|---|
Formato: | article |
Lenguaje: | ZH |
Publicado: |
Hebei University of Science and Technology
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/10f1567acea3403b8f0bc06efc57c887 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:10f1567acea3403b8f0bc06efc57c887 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:10f1567acea3403b8f0bc06efc57c8872021-11-23T07:16:39ZA facial expression recognition method based on face texture feature fusion1008-154210.7535/hbkd.2021yx02004https://doaj.org/article/10f1567acea3403b8f0bc06efc57c8872021-04-01T00:00:00Zhttp://xuebao.hebust.edu.cn/hbkjdx/ch/reader/create_pdf.aspx?file_no=b202102004&flag=1&journal_https://doaj.org/toc/1008-1542Aiming at facial expression recognition, the recognition rate is not high due to noise and occlusion. A hybrid approach of facial expression has been presented by combining local and global features. First, feature extraction is performed to fuse the histogram of oriented gradients (HOG) descriptor with the compounded local ternary pattern (C-LTP) descriptor. Second, features extracted by HOG and C-LTP are fused into a single feature vector. Third, the feature vector is sent to a multi-class support vector machine classifier for facial classification. Finally, the proposed method is compared with the existing facial expression recognition methods in three public facial expression image databases, and the results show that the recognition rates of the proposed method in MMI, JAFFE and CK[KG-*2]+ databases are 98.28%, 95.75% and 99.64%, respectively. The average recognition rate is 10% higher than other methods, which is better than other existing methods. The results of this study provide a reference for the research of facial expression recognition in many situations. The method of facial expression recognition proposed can effectively promote the development of human-computer interaction system and the study of computer image understanding. It is of great significance to realize the fusion of human language and natural language, as well as the establishment and implementation of the connection model between language and expression.Tingting GAOHang LIShoulin YINHebei University of Science and Technologyarticlepattern recognition; facial expression recognition; feature fusion; hog; c-ltp; support vector machineTechnologyTZHJournal of Hebei University of Science and Technology, Vol 42, Iss 2, Pp 119-126 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
ZH |
topic |
pattern recognition; facial expression recognition; feature fusion; hog; c-ltp; support vector machine Technology T |
spellingShingle |
pattern recognition; facial expression recognition; feature fusion; hog; c-ltp; support vector machine Technology T Tingting GAO Hang LI Shoulin YIN A facial expression recognition method based on face texture feature fusion |
description |
Aiming at facial expression recognition, the recognition rate is not high due to noise and occlusion. A hybrid approach of facial expression has been presented by combining local and global features. First, feature extraction is performed to fuse the histogram of oriented gradients (HOG) descriptor with the compounded local ternary pattern (C-LTP) descriptor. Second, features extracted by HOG and C-LTP are fused into a single feature vector. Third, the feature vector is sent to a multi-class support vector machine classifier for facial classification. Finally, the proposed method is compared with the existing facial expression recognition methods in three public facial expression image databases, and the results show that the recognition rates of the proposed method in MMI, JAFFE and CK[KG-*2]+ databases are 98.28%, 95.75% and 99.64%, respectively. The average recognition rate is 10% higher than other methods, which is better than other existing methods. The results of this study provide a reference for the research of facial expression recognition in many situations. The method of facial expression recognition proposed can effectively promote the development of human-computer interaction system and the study of computer image understanding. It is of great significance to realize the fusion of human language and natural language, as well as the establishment and implementation of the connection model between language and expression. |
format |
article |
author |
Tingting GAO Hang LI Shoulin YIN |
author_facet |
Tingting GAO Hang LI Shoulin YIN |
author_sort |
Tingting GAO |
title |
A facial expression recognition method based on face texture feature fusion |
title_short |
A facial expression recognition method based on face texture feature fusion |
title_full |
A facial expression recognition method based on face texture feature fusion |
title_fullStr |
A facial expression recognition method based on face texture feature fusion |
title_full_unstemmed |
A facial expression recognition method based on face texture feature fusion |
title_sort |
facial expression recognition method based on face texture feature fusion |
publisher |
Hebei University of Science and Technology |
publishDate |
2021 |
url |
https://doaj.org/article/10f1567acea3403b8f0bc06efc57c887 |
work_keys_str_mv |
AT tingtinggao afacialexpressionrecognitionmethodbasedonfacetexturefeaturefusion AT hangli afacialexpressionrecognitionmethodbasedonfacetexturefeaturefusion AT shoulinyin afacialexpressionrecognitionmethodbasedonfacetexturefeaturefusion AT tingtinggao facialexpressionrecognitionmethodbasedonfacetexturefeaturefusion AT hangli facialexpressionrecognitionmethodbasedonfacetexturefeaturefusion AT shoulinyin facialexpressionrecognitionmethodbasedonfacetexturefeaturefusion |
_version_ |
1718416808150564864 |