2014
DOI: 10.9790/3021-04430105
|View full text |Cite
|
Sign up to set email alerts
|

A Survey of Facial Expression Recognition Methods

Abstract: -Facial expression recognition (anger, sad, happy, disgust, surprise, fear expressions) is application of advanced object detection, pattern recognition and classification task. Facial expression is one of the most powerful and natural means for human beings to show their emotions. It has found its applications in humancomputer interaction (HCI), robotics, border security systems, forensics, machine vision, video conferencing, user profiling for customer satisfaction, physiological research etc. Although human… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2014
2014
2020
2020

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(2 citation statements)
references
References 12 publications
(7 reference statements)
0
2
0
Order By: Relevance
“…According to Swets and Weng [17], PCA derives the most expressive features, but may not embed sufficient discriminating power. In addition to PCA, Fisher Linear Discriminant (FLD) is another commonly used feature reduction technique which is claimed to provide comparatively more class separability by maximizing the mean between classes and minimizing the variation within a class [3,18,19]. Thus FLD projects the most discriminative features for class distinction.…”
Section: Feature Selectionmentioning
confidence: 99%
“…According to Swets and Weng [17], PCA derives the most expressive features, but may not embed sufficient discriminating power. In addition to PCA, Fisher Linear Discriminant (FLD) is another commonly used feature reduction technique which is claimed to provide comparatively more class separability by maximizing the mean between classes and minimizing the variation within a class [3,18,19]. Thus FLD projects the most discriminative features for class distinction.…”
Section: Feature Selectionmentioning
confidence: 99%
“…A typical static facial expression recognition approach could be divided into four main components [3] face detection, face alignment, feature extraction and finally classification. As for the step of feature extraction of expression, most of the recent approaches presented in the literature design a handcrafted feature extraction method or uses a combination of many features [4]. In contrast, this paper is based on rich deep features extracted using Deep Convolutional Neural Networks 1 (CNNs) [5].…”
Section: Introductionmentioning
confidence: 99%