Facial Expression Recognition in the Wild Using Convolutional Neural Networks
Facial Expression Recognition (FER) is the task of predicting a specific facial expression given a facial image. FER has demonstrated remarkable progress due to the advancement of deep learning. Generally, a FER system as a prediction model is built using two sub-modules: 1. Facial image representat...
Main Author: | |
---|---|
Format: | Text |
Language: | unknown |
Published: |
DigitalCommons@USU
2020
|
Subjects: | |
Online Access: | https://digitalcommons.usu.edu/etd/7851 https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=8991&context=etd |
id |
ftutahsudc:oai:digitalcommons.usu.edu:etd-8991 |
---|---|
record_format |
openpolar |
spelling |
ftutahsudc:oai:digitalcommons.usu.edu:etd-8991 2023-05-15T16:01:44+02:00 Facial Expression Recognition in the Wild Using Convolutional Neural Networks Farzaneh, Amir Hossein 2020-08-01T07:00:00Z application/pdf https://digitalcommons.usu.edu/etd/7851 https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=8991&context=etd unknown DigitalCommons@USU https://digitalcommons.usu.edu/etd/7851 https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=8991&context=etd Copyright for this work is held by the author. Transmission or reproduction of materials protected by copyright beyond that allowed by fair use requires the written permission of the copyright owners. Works not in the public domain cannot be commercially exploited without permission of the copyright owner. Responsibility for any use rests exclusively with the user. For more information contact digitalcommons@usu.edu. PDM All Graduate Theses and Dissertations facial expression recognition wild convolutional neural network deep learning discriminant loss function attention adaptive emotion Computer Sciences text 2020 ftutahsudc 2022-03-07T22:00:19Z Facial Expression Recognition (FER) is the task of predicting a specific facial expression given a facial image. FER has demonstrated remarkable progress due to the advancement of deep learning. Generally, a FER system as a prediction model is built using two sub-modules: 1. Facial image representation model that learns a mapping from the input 2D facial image to a compact feature representation in the embedding space, and 2. A classifier module that maps the learned features to the label space comprising seven labels of neutral, happy, sad, surprise, anger, fear, or disgust. Ultimately, the prediction model aims to predict one of the seven aforementioned labels for the given input image. This process is carried out using a supervised learning algorithm where the model minimizes an objective function that measures the error between the prediction and true label by searching for the best mapping function. Our work is inspired by Deep Metric Learning (DML) approaches to learn an efficient embedding space for the classifier module. DML fundamentally aims to achieve maximal separation in the embedding space by creating compact and well-separated clusters with the capability of feature discrimination. However, conventional DML methods ignore the underlying challenges associated with wild FER datasets, where images exhibit large intra-class variation and inter-class similarity. First, we tackle the extreme class imbalance that leads to a separation bias toward facial expression classes populated with more data (e.g., happy and neutral) against minority classes (e.g., disgust and fear). To eliminate this bias, we propose a discriminant objective function to optimize the embedding space to enforce inter-class separation of features for both majority and minority classes. Second, we design an adaptive mechanism to selectively discriminate features in the embedding space to promote generalization to yield a prediction model that classifies unseen images more accurately. We are inspired by the human visual attention model described as the perception of the most salient visual cues in the observed scene. Accordingly, our attentive mechanism adaptively selects important features to discriminate in the DML's objective function. We conduct experiments on two popular large-scale wild FER datasets (RAF-DB and AffectNet) to show the enhanced discriminative power of our proposed methods compared with several state-of-the-art FER methods. Text DML Utah State University: DigitalCommons@USU |
institution |
Open Polar |
collection |
Utah State University: DigitalCommons@USU |
op_collection_id |
ftutahsudc |
language |
unknown |
topic |
facial expression recognition wild convolutional neural network deep learning discriminant loss function attention adaptive emotion Computer Sciences |
spellingShingle |
facial expression recognition wild convolutional neural network deep learning discriminant loss function attention adaptive emotion Computer Sciences Farzaneh, Amir Hossein Facial Expression Recognition in the Wild Using Convolutional Neural Networks |
topic_facet |
facial expression recognition wild convolutional neural network deep learning discriminant loss function attention adaptive emotion Computer Sciences |
description |
Facial Expression Recognition (FER) is the task of predicting a specific facial expression given a facial image. FER has demonstrated remarkable progress due to the advancement of deep learning. Generally, a FER system as a prediction model is built using two sub-modules: 1. Facial image representation model that learns a mapping from the input 2D facial image to a compact feature representation in the embedding space, and 2. A classifier module that maps the learned features to the label space comprising seven labels of neutral, happy, sad, surprise, anger, fear, or disgust. Ultimately, the prediction model aims to predict one of the seven aforementioned labels for the given input image. This process is carried out using a supervised learning algorithm where the model minimizes an objective function that measures the error between the prediction and true label by searching for the best mapping function. Our work is inspired by Deep Metric Learning (DML) approaches to learn an efficient embedding space for the classifier module. DML fundamentally aims to achieve maximal separation in the embedding space by creating compact and well-separated clusters with the capability of feature discrimination. However, conventional DML methods ignore the underlying challenges associated with wild FER datasets, where images exhibit large intra-class variation and inter-class similarity. First, we tackle the extreme class imbalance that leads to a separation bias toward facial expression classes populated with more data (e.g., happy and neutral) against minority classes (e.g., disgust and fear). To eliminate this bias, we propose a discriminant objective function to optimize the embedding space to enforce inter-class separation of features for both majority and minority classes. Second, we design an adaptive mechanism to selectively discriminate features in the embedding space to promote generalization to yield a prediction model that classifies unseen images more accurately. We are inspired by the human visual attention model described as the perception of the most salient visual cues in the observed scene. Accordingly, our attentive mechanism adaptively selects important features to discriminate in the DML's objective function. We conduct experiments on two popular large-scale wild FER datasets (RAF-DB and AffectNet) to show the enhanced discriminative power of our proposed methods compared with several state-of-the-art FER methods. |
format |
Text |
author |
Farzaneh, Amir Hossein |
author_facet |
Farzaneh, Amir Hossein |
author_sort |
Farzaneh, Amir Hossein |
title |
Facial Expression Recognition in the Wild Using Convolutional Neural Networks |
title_short |
Facial Expression Recognition in the Wild Using Convolutional Neural Networks |
title_full |
Facial Expression Recognition in the Wild Using Convolutional Neural Networks |
title_fullStr |
Facial Expression Recognition in the Wild Using Convolutional Neural Networks |
title_full_unstemmed |
Facial Expression Recognition in the Wild Using Convolutional Neural Networks |
title_sort |
facial expression recognition in the wild using convolutional neural networks |
publisher |
DigitalCommons@USU |
publishDate |
2020 |
url |
https://digitalcommons.usu.edu/etd/7851 https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=8991&context=etd |
genre |
DML |
genre_facet |
DML |
op_source |
All Graduate Theses and Dissertations |
op_relation |
https://digitalcommons.usu.edu/etd/7851 https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=8991&context=etd |
op_rights |
Copyright for this work is held by the author. Transmission or reproduction of materials protected by copyright beyond that allowed by fair use requires the written permission of the copyright owners. Works not in the public domain cannot be commercially exploited without permission of the copyright owner. Responsibility for any use rests exclusively with the user. For more information contact digitalcommons@usu.edu. |
op_rightsnorm |
PDM |
_version_ |
1766397474153431040 |