Proceedings of the 2013 IEEE/SICE International Symposium on System Integration 2013
DOI: 10.1109/sii.2013.6776664
|View full text |Cite
|
Sign up to set email alerts
|

Feature fusion of HOG and WLD for facial expression recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
22
0
1

Year Published

2015
2015
2024
2024

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 40 publications
(23 citation statements)
references
References 20 publications
0
22
0
1
Order By: Relevance
“…Afterward, the facial expression is recognized by using the constructed feature vectors either indirectly as a collection of facial action units (see FACS system [9]) or directly as one of the prototypical emotions [30], whereat very diverse classifiers were used ranging from k-nearest neighbor (kNN) [34], family of Bayes classifiers [4], support vector machines (SVM), hidden Markov model (HMM) [32], etc., combined by principal component analysis (PCA), independent component analysis (ICA) [2], and linear discriminant analysis (LDA). It should be stressed that recognition approaches may also be classified as frame-based or video sequence-based, depending on whether temporal information is used [30].…”
Section: Introductionmentioning
confidence: 99%
See 3 more Smart Citations
“…Afterward, the facial expression is recognized by using the constructed feature vectors either indirectly as a collection of facial action units (see FACS system [9]) or directly as one of the prototypical emotions [30], whereat very diverse classifiers were used ranging from k-nearest neighbor (kNN) [34], family of Bayes classifiers [4], support vector machines (SVM), hidden Markov model (HMM) [32], etc., combined by principal component analysis (PCA), independent component analysis (ICA) [2], and linear discriminant analysis (LDA). It should be stressed that recognition approaches may also be classified as frame-based or video sequence-based, depending on whether temporal information is used [30].…”
Section: Introductionmentioning
confidence: 99%
“…Recently, a histogram of oriented gradient (HOG) descriptor has attracted the attention of the facial expression recognition research community due to its invariance to geometric (except object orientation) and photometric transformations. This texture descriptor has been applied in several methods for human emotion recognition from a single 2D facial image, e.g., in [7,14,23,34]. The highest recognition rate amongst them was obtained in [34] by combining the HOG descriptor and the Weber local descriptor (WLD), whereas kNN was used as classifier.…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations
“…Este descritor de textura tem sido empregado com sucesso em aplicações de reconhecimento de expressões faciais, como abordado no trabalho de Liu, Zhang e Liu (2014), por Wang et al (2013) e em Hussain et al (2014). No entanto não foi encontrado na literatura nenhum trabalho que explore a análise da textura da íris com este descritor, somente uma nova abordagem baseada no WLD para extração de características da íris bovina (SUN; ZHAO; YANG, 2013).…”
Section: Aplicações Do Wld Em Reconhecimento De íRisunclassified