Melola Discovery

← Melola Discovery

Jurnal SINTA 2

Facial Expression Recognition using Residual Convnet with Image Augmentations

Jurnal Ilmu Komputer dan Informasi (JIKI) · Vol. 14 No. 2 (2021) · pp. 127–135

DOI
10.21609/jiki.v14i2.968
ISSN
2502-9274, 2088-7051
Published
2021-07-04
Publisher
Faculty of Computer Science - Universitas Indonesia
Language
eng

Abstract

During the COVID-19 pandemic, many offline activities are turned into online activities via video meetings to prevent the spread of the COVID 19 virus. In the online video meeting, some micro-interactions are missing when compared to direct social interactions. The use of machines to assist facial expression recognition in online video meetings is expected to increase understanding of the interactions among users. Many studies have shown that CNN-based neural networks are quite effective and accurate in image classification. In this study, some open facial expression datasets were used to train CNN-based neural networks with a total number of training data of 342,497 images. This study gets the best results using ResNet-50 architecture with Mish activation function and Accuracy Booster Plus block. This architecture is trained using the Ranger and Gradient Centralization optimization method for 60000 steps with a batch size of 256. The best results from the training result in accuracy of AffectNet validation data of 0.5972, FERPlus validation data of 0.8636, FERPlus test data of 0.8488, and RAF-DB test data of 0.8879. From this study, the proposed method outperformed plain ResNet in all test scenarios without transfer learning, and there is a potential for better performance with the pre-training model. The code is available at https://github.com/yusufrahadika-facial-expressions-essay.

Keywords

Collaboration network of the authors

40 authors · 85 co-authorship links · 5 across different organisations · showing the 40 most connected

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • University of Brawijaya
  • Institut Teknologi Sepuluh Nopember
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Indriati IndriatiUniversity of Brawijaya2
Fitra Abdurrachman BachtiarUniversity of Brawijaya2
Achmad RidokUniversity of Brawijaya2
Agus Zainal ArifinInstitut Teknologi Sepuluh Nopember1
Evy Kamilah RatnasariInstitut Teknologi Sepuluh Nopember1
Siti MutrofinInstitut Teknologi Sepuluh Nopember1
Chastine FatichahInstitut Teknologi Sepuluh Nopember1
Ratih Kartika DewiUniversity of Brawijaya1
Putra Pandu AdikaraUniversity of Brawijaya1
Sigit AdinugrohoUniversity of Brawijaya1
Agus Wahyu WidodoUniversity of Brawijaya1
Bayu RahayudiUniversity of Brawijaya1
Rizky Maulana IqbalUniversity of Brawijaya1
Edy SantosoUniversity of Brawijaya1
Raditya RinandyaswaraUniversity of Brawijaya1
Muhammad Tanzil FurqonUniversity of Brawijaya1
Rifki Akbar SiregarUniversity of Brawijaya1
M. Sofyan IrwantoUniversity of Brawijaya1
Candra DewiUniversity of Brawijaya1
Nurfatima SelleUniversity of Brawijaya1
Zainal ArifienUniversity of Brawijaya1
Fitra Abdurrahman BachtiarAffiliation unknown1
Alfisyar Jefry PranataUniversity of Brawijaya1
Edy SantosoUniversity of Brawijaya1
Natasya Eldha OktavianaUniversity of Brawijaya1
Alvin Tarisa AkbarUniversity of Brawijaya1
Michael Stephen LuiUniversity of Brawijaya1
Daniel Geoffrey ManurungUniversity of Brawijaya1
Mohammad Ryan PinasthikaUniversity of Brawijaya1
Muhammad Azka Obila VasyaUniversity of Brawijaya1
Rania Aprilia Dwi Setya PutriUniversity of Brawijaya1
Agustinus Parasian TampubolonUniversity of Brawijaya1
Rakan Fadhil PrayataUniversity of Brawijaya1
Septia Khoirin NisaUniversity of Brawijaya1
Assyfa Rasida HanumUniversity of Brawijaya1
Ivykaeyla Adriana ZethaUniversity of Brawijaya1
Lailil MuflikhahUniversity of Brawijaya1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://jiki.cs.ui.ac.id/index.php/jiki/oai, first harvested 26 Okt 2026, last seen 26 Okt 2026.
Original metadata (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Facial Expression Recognition using Residual Convnet with Image Augmentations</dc:title>
	<dc:creator>Rahadika, Fadhil Yusuf</dc:creator>
	<dc:creator>Yudistira, Novanto</dc:creator>
	<dc:creator>Sari, Yuita Arum</dc:creator>
	<dc:subject xml:lang="en-US">facial expression recognition</dc:subject>
	<dc:subject xml:lang="en-US">CNN</dc:subject>
	<dc:subject xml:lang="en-US">ResNet</dc:subject>
	<dc:subject xml:lang="en-US">Mish</dc:subject>
	<dc:subject xml:lang="en-US">Accuracy Booster Plus</dc:subject>
	<dc:description xml:lang="en-US">During the COVID-19 pandemic, many offline activities are turned into online activities via video meetings to prevent the spread of the COVID 19 virus. In the online video meeting, some micro-interactions are missing when compared to direct social interactions. The use of machines to assist facial expression recognition in online video meetings is expected to increase understanding of the interactions among users. Many studies have shown that CNN-based neural networks are quite effective and accurate in image classification. In this study, some open facial expression datasets were used to train CNN-based neural networks with a total number of training data of 342,497 images. This study gets the best results using ResNet-50 architecture with Mish activation function and Accuracy Booster Plus block. This architecture is trained using the Ranger and Gradient Centralization optimization method for 60000 steps with a batch size of 256. The best results from the training result in accuracy of AffectNet validation data of 0.5972, FERPlus validation data of 0.8636, FERPlus test data of 0.8488, and RAF-DB test data of 0.8879. From this study, the proposed method outperformed plain ResNet in all test scenarios without transfer learning, and there is a potential for better performance with the pre-training model. The code is available at https://github.com/yusufrahadika-facial-expressions-essay.</dc:description>
	<dc:publisher xml:lang="en-US">Faculty of Computer Science  - Universitas Indonesia</dc:publisher>
	<dc:date>2021-07-04</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://jiki.cs.ui.ac.id/index.php/jiki/article/view/968</dc:identifier>
	<dc:identifier>10.21609/jiki.v14i2.968</dc:identifier>
	<dc:source xml:lang="en-US">Jurnal Ilmu Komputer dan Informasi; Vol. 14 No. 2 (2021): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information); 127-135</dc:source>
	<dc:source>2502-9274</dc:source>
	<dc:source>2088-7051</dc:source>
	<dc:source>10.21609/jiki.v14i2</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://jiki.cs.ui.ac.id/index.php/jiki/article/view/968/448</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2021 Jurnal Ilmu Komputer dan Informasi</dc:rights>
</oai_dc:dc>