Complex Emotion Estimation Using Analysis-by-Synthesis of Facial Expression Images

This research proposes an approach for recognizing facial expressions for complex emotion estimation through the utilization of generated facial images. The proposed approach consists of two main parts: facial image generation and facial expression recognition. In the first part, we introduce Condit...

Full description

Saved in:
Bibliographic Details
Main Authors: Win Shwe Sin Khine, Prarinya Siritanawan, Kazunori Kotani
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11004126/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714494979178496
author Win Shwe Sin Khine
Prarinya Siritanawan
Kazunori Kotani
author_facet Win Shwe Sin Khine
Prarinya Siritanawan
Kazunori Kotani
author_sort Win Shwe Sin Khine
collection DOAJ
description This research proposes an approach for recognizing facial expressions for complex emotion estimation through the utilization of generated facial images. The proposed approach consists of two main parts: facial image generation and facial expression recognition. In the first part, we introduce Conditioned Emotion Generative Adversarial Networks (cEmoGANs) to synthesize images that convey complex facial expressions. Unlike previous methods, our generative model maintains face identity information and expresses various types of complex emotions. This capability encourages the generator to have control over the image generation process, resulting in enhanced image quality, reduced distortion, and increased diversity of generated images. The second part involves the design of a multiple-label classification based on a convolutional neural network trained on the complex facial expression images generated from the first part, which is employed in the recognition of complex facial expressions for emotion estimation. Our model, using images generated by cEmoGANs, demonstrates a notable performance surpassing the capabilities of the previous models in comparative evaluations.
format Article
id doaj-art-4c60935cc5ee40129ae8496e786dfa72
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-4c60935cc5ee40129ae8496e786dfa722025-08-20T03:13:42ZengIEEEIEEE Access2169-35362025-01-0113887318874610.1109/ACCESS.2025.357016711004126Complex Emotion Estimation Using Analysis-by-Synthesis of Facial Expression ImagesWin Shwe Sin Khine0Prarinya Siritanawan1https://orcid.org/0000-0002-9023-3208Kazunori Kotani2School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, JapanDepartment of Engineering, Graduate School of Science and Technology, Informatics and Interdisciplinary Systems Division, Shinshu University, Nagano, JapanFaculty of Transdisciplinary Science, Institute of Philosophy in Interdisciplinary Science, Kanazawa University, Kanazawa, Ishikawa, JapanThis research proposes an approach for recognizing facial expressions for complex emotion estimation through the utilization of generated facial images. The proposed approach consists of two main parts: facial image generation and facial expression recognition. In the first part, we introduce Conditioned Emotion Generative Adversarial Networks (cEmoGANs) to synthesize images that convey complex facial expressions. Unlike previous methods, our generative model maintains face identity information and expresses various types of complex emotions. This capability encourages the generator to have control over the image generation process, resulting in enhanced image quality, reduced distortion, and increased diversity of generated images. The second part involves the design of a multiple-label classification based on a convolutional neural network trained on the complex facial expression images generated from the first part, which is employed in the recognition of complex facial expressions for emotion estimation. Our model, using images generated by cEmoGANs, demonstrates a notable performance surpassing the capabilities of the previous models in comparative evaluations.https://ieeexplore.ieee.org/document/11004126/Complex emotionsanalysis-by-synthesisconditioned emotion generative adversarial networksemotions estimation
spellingShingle Win Shwe Sin Khine
Prarinya Siritanawan
Kazunori Kotani
Complex Emotion Estimation Using Analysis-by-Synthesis of Facial Expression Images
IEEE Access
Complex emotions
analysis-by-synthesis
conditioned emotion generative adversarial networks
emotions estimation
title Complex Emotion Estimation Using Analysis-by-Synthesis of Facial Expression Images
title_full Complex Emotion Estimation Using Analysis-by-Synthesis of Facial Expression Images
title_fullStr Complex Emotion Estimation Using Analysis-by-Synthesis of Facial Expression Images
title_full_unstemmed Complex Emotion Estimation Using Analysis-by-Synthesis of Facial Expression Images
title_short Complex Emotion Estimation Using Analysis-by-Synthesis of Facial Expression Images
title_sort complex emotion estimation using analysis by synthesis of facial expression images
topic Complex emotions
analysis-by-synthesis
conditioned emotion generative adversarial networks
emotions estimation
url https://ieeexplore.ieee.org/document/11004126/
work_keys_str_mv AT winshwesinkhine complexemotionestimationusinganalysisbysynthesisoffacialexpressionimages
AT prarinyasiritanawan complexemotionestimationusinganalysisbysynthesisoffacialexpressionimages
AT kazunorikotani complexemotionestimationusinganalysisbysynthesisoffacialexpressionimages