Machine learning based face expression recognition

Face expression recognition is an active research area in the past two decades. Many attempts have been made to understand how human beings perceive human faces. It is widely accepted that face recognition may rely on both componential cues (such as eyes, mouth, nose, and cheeks) and non compone...

Full description

Saved in:
Bibliographic Details
Main Author: Paing Thu Thu Aung
Other Authors: Jiang Xudong
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/158367
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-158367
record_format dspace
spelling sg-ntu-dr.10356-1583672023-07-07T19:18:25Z Machine learning based face expression recognition Paing Thu Thu Aung Jiang Xudong School of Electrical and Electronic Engineering EXDJiang@ntu.edu.sg Engineering::Electrical and electronic engineering::Computer hardware, software and systems Face expression recognition is an active research area in the past two decades. Many attempts have been made to understand how human beings perceive human faces. It is widely accepted that face recognition may rely on both componential cues (such as eyes, mouth, nose, and cheeks) and non componential/holistic cues (considering the face as whole rather than as separate parts). However, how these cues should be optimally integrated remains unclear. Most state-of-the-art technologies of face expression recognition employ either componential cues or holistic information. Their recognition performance is therefore limited. This project investigates ways to integrate componential and holistic cues. We deployed a pretrained facial landmark detector to locate 68 landmarks of a face, to extract 8 individual facial components. Next, we utilized a convolutional network (CNN) to extract and learn relevant features from the facial and 8 componential images. Moreover, we deployed a CatBoost classifier to classify the landmark coordinates. Finally, we deployed soft and hard voting to combine all the predictions of the 10 trained models together. The soft voting approach achieved an accuracy of 63.87%, which is comparable to some existing method, considering we deployed fewer data for training. The creative approach may potentially lead to a better face expression recognition technology that outperforms current existing methods. Bachelor of Engineering (Electrical and Electronic Engineering) 2022-06-03T02:59:08Z 2022-06-03T02:59:08Z 2022 Final Year Project (FYP) Paing Thu Thu Aung (2022). Machine learning based face expression recognition. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/158367 https://hdl.handle.net/10356/158367 en P3042-202 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering::Computer hardware, software and systems
spellingShingle Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Paing Thu Thu Aung
Machine learning based face expression recognition
description Face expression recognition is an active research area in the past two decades. Many attempts have been made to understand how human beings perceive human faces. It is widely accepted that face recognition may rely on both componential cues (such as eyes, mouth, nose, and cheeks) and non componential/holistic cues (considering the face as whole rather than as separate parts). However, how these cues should be optimally integrated remains unclear. Most state-of-the-art technologies of face expression recognition employ either componential cues or holistic information. Their recognition performance is therefore limited. This project investigates ways to integrate componential and holistic cues. We deployed a pretrained facial landmark detector to locate 68 landmarks of a face, to extract 8 individual facial components. Next, we utilized a convolutional network (CNN) to extract and learn relevant features from the facial and 8 componential images. Moreover, we deployed a CatBoost classifier to classify the landmark coordinates. Finally, we deployed soft and hard voting to combine all the predictions of the 10 trained models together. The soft voting approach achieved an accuracy of 63.87%, which is comparable to some existing method, considering we deployed fewer data for training. The creative approach may potentially lead to a better face expression recognition technology that outperforms current existing methods.
author2 Jiang Xudong
author_facet Jiang Xudong
Paing Thu Thu Aung
format Final Year Project
author Paing Thu Thu Aung
author_sort Paing Thu Thu Aung
title Machine learning based face expression recognition
title_short Machine learning based face expression recognition
title_full Machine learning based face expression recognition
title_fullStr Machine learning based face expression recognition
title_full_unstemmed Machine learning based face expression recognition
title_sort machine learning based face expression recognition
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/158367
_version_ 1772827616435240960