Melola Discovery

← Melola Discovery

Open access Jurnal SINTA 2

Face Image Generation and Enhancement Using Conditional Generative Adversarial Network

IJCCS (Indonesian Journal of Computing and Cybernetics Systems) · Vol. 16 No. 1 (2022) · pp. 1–10

DOI
10.22146/ijccs.58327
ISSN
2460-7258, 1978-1520
Published
2022-01-31
Publisher
IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.
Language
eng
License
creativecommons.org/licenses/by-sa/4.0

Abstract

The accuracy and speed of a single image super-resolution using a convolutional neural network is often a problem in improving finer texture details when using large enhancement factors. Some recent studies have focused on minimal mean square error, resulting in a high peak signal to noise ratio. Generally, although the peak signal to noise ratio has a high value, the output image is less detailed. This shows that the determination of super-resolution is not optimal. Conditional Generative Adversarial Network based on Boundary Equilibrium Generative Adversarial Network, by combining Mean Square Error Loss and GAN Loss as a loss function to optimize the super-resolution model and produce super-resolution images. Also, the generator network is designed with skip connection architecture to increase convergence speed and strengthen feature distribution. Image quality value parameters used in this study are Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The results showed the highest image quality values using dataset validation were 26.55 for PSNR values and 0.93 for SSIM values. The highest image quality values using the testing dataset are 24.56 for the PSNR value and 0.91 for the SSIM value.

Keywords

Collaboration network of the authors

40 authors · 58 co-authorship links · 11 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.

  • Universitas Gadjah Mada
  • IPB University
  • Universitas Lamappapoleonro
  • Diponegoro University
  • Universitas 'Aisyiyah Surakarta
  • Universitas Teknokrat Indonesia
  • Sebelas Maret University
  • Other organisations
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Retantyo WardoyoUniversitas Gadjah Mada6
Aina MusdholifahUniversitas Gadjah Mada2
Azhari SnUniversitas Gadjah Mada2
Yohanes SuyantoUniversitas Gadjah Mada2
Agus HarjokoUniversitas Gadjah Mada2
Sri NurdiatiIPB University1
Jati Sasongko WibowoAffiliation unknown1
Aridhanyati ArifinAffiliation unknown1
Jamila JamilaAffiliation unknown1
Rio KurniawanUniversitas Gadjah Mada1
Rita WiryasaputraUniversitas Gadjah Mada1
Sri Fitri WahyuniAffiliation unknown1
Sherly JayantiAffiliation unknown1
Salahuddin SalahuddinUniversitas Gadjah Mada1
Tedy RismawanUniversitas Gadjah Mada1
Muhammad Lhsan SaritaAffiliation unknown1
Rusdi EfendiAffiliation unknown1
Rukli RukliUniversitas Lamappapoleonro1
Khadijah KhadijahDiponegoro University1
Jani KusantiUniversitas 'Aisyiyah Surakarta1
Hence Beedwel LumentutAffiliation unknown1
Annisa MaulianiUniversitas Gadjah Mada1
Eka WahyudiAffiliation unknown1
Ari Kusuma WardanaUniversitas Gadjah Mada1
Maulida Ayu FitrianiUniversitas Gadjah Mada1
Abram Setyo PrabowoUniversitas Gadjah Mada1
Yayang Eluis Bali MawartikaUniversitas Gadjah Mada1
Muhammad Asaduddin HazaziUniversitas Gadjah Mada1
Auliya Rahman IsnainUniversitas Teknokrat Indonesia1
Achmad Siddik FathoniUniversitas Gadjah Mada1
Annisaa UtamiUniversitas Gadjah Mada1
Astrid Noviana ParadhitaSebelas Maret University1
Anny Kartika SariUniversitas Gadjah Mada1
Dian EkapratiwiUniversitas Gadjah Mada1
Azhari SubanarAffiliation unknown1
Kusrini KusriniUniversitas Amikom Yogyakarta1
Azhari AzhariUniversitas Gadjah Mada1

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://journal.ugm.ac.id/ijccs/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">Face Image Generation and Enhancement Using Conditional Generative Adversarial Network</dc:title>
	<dc:creator>Mardiah, Ainil</dc:creator>
	<dc:creator>Hartati, Sri</dc:creator>
	<dc:creator>Sihabuddin, Agus</dc:creator>
	<dc:subject xml:lang="en-US">computer science</dc:subject>
	<dc:subject xml:lang="en-US">Conditional GAN; Boundary Equilibrium; Single Image Super-Resolution</dc:subject>
	<dc:description xml:lang="en-US">The accuracy and speed of a single image super-resolution using a convolutional neural network is often a problem in improving finer texture details when using large enhancement factors. Some recent studies have focused on minimal mean square error, resulting in a high peak signal to noise ratio. Generally, although the peak signal to noise ratio has a high value, the output image is less detailed. This shows that the determination of super-resolution is not optimal. Conditional Generative Adversarial Network based on Boundary Equilibrium Generative Adversarial Network, by combining Mean Square Error Loss and GAN Loss as a loss function to optimize the super-resolution model and produce super-resolution images. Also, the generator network is designed with skip connection architecture to increase convergence speed and strengthen feature distribution. Image quality value parameters used in this study are Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The results showed the highest image quality values using dataset validation were 26.55 for PSNR values and 0.93 for SSIM values. The highest image quality values using the testing dataset are 24.56 for the PSNR value and 0.91 for the SSIM value.</dc:description>
	<dc:publisher xml:lang="en-US">IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.</dc:publisher>
	<dc:contributor xml:lang="en-US"></dc:contributor>
	<dc:date>2022-01-31</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.ugm.ac.id/ijccs/article/view/58327</dc:identifier>
	<dc:identifier>10.22146/ijccs.58327</dc:identifier>
	<dc:source xml:lang="en-US">IJCCS (Indonesian Journal of Computing and Cybernetics Systems); Vol 16, No 1 (2022): January; 1-10</dc:source>
	<dc:source>2460-7258</dc:source>
	<dc:source>1978-1520</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.ugm.ac.id/ijccs/article/view/58327/33158</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2022 IJCCS (Indonesian Journal of Computing and Cybernetics Systems)</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>