Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Enhancing realism in handwritten text images with generative adversarial networks

Bulletin of Electrical Engineering and Informatics · Vol. 14 No. 3 (2025) · hlm. 2370–2379

DOI
10.11591/eei.v14i3.9190
ISSN
2089-3191, 2302-9285
Terbit
2025-05-02
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

Image synthesis is particularly important for applications that want to create realistic handwritten documents, which is why handwritten text generation is a critical area within its domain. Even with today's highly advanced technology, generating diverse and accurate representations of human handwriting is still a tough problem because of the variability in style. In this study, we tackle the problem of instability during the training phase of generative adversarial networks (GANs) for generating handwritten text images. Using the MNIST dataset, which includes 60,000 training and 10,000 test images of handwritten digits, we trained a GAN model to generate synthetic handwritten images. The methodology involves optimizing both the generator and discriminator using adversarial training, binary cross-entropy loss, as well as the optimizer Adam. A brand-new decaying learning rate schedule was introduced to speed up convergence. Performance was evaluated using the Fréchet inception distance (FID) metric. The results show that this model effectively generated high-quality synthetic images of handwritten digits, which resembled real data closely in the face of it all and also that there was a steady reduction in FID scores across epochs indicating improved performance.

Kata kunci

Jaringan kolaborasi para penulis

19 penulis · 64 tautan kepenulisan bersama · 43 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • MIT World Peace University
  • Symbiosis International University
  • Raisoni Group of Institutions
  • Amity University Chhatisgarh
  • Pandit Sundarlal Sharma Open University
  • Yashwantrao Chavan Maharashtra Open University
  • Noida International University
  • Organisasi lain
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Akshita ChanchlaniMIT World Peace University3
Parul DubeySymbiosis International University3
Murtuza MurtuzaMIT World Peace University3
Gunjan KeswaniAfiliasi tidak diketahui3
Amit MishraMIT World Peace University3
Rashid MahmoodGuru Nanak Dev University3
Titiksha Tulsidas BhagatAfiliasi tidak diketahui2
Ankit V. KokareMIT World Peace University2
Poonam Ramesh ChaudhariYashwantrao Chavan Maharashtra Open University2
Umesh K. RautMIT World Peace University2
Gaurav Vishnu LondheSymbiosis International University2
Amit MishraMIT World Peace University1
Aruna SinghNoida International University1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Enhancing realism in handwritten text images with generative adversarial networks</dc:title><dc:creator>Parul Dubey</dc:creator><dc:creator>Manjushree Nayak</dc:creator><dc:creator>Hitesh Gehani</dc:creator><dc:creator>Ashwini Kukade</dc:creator><dc:creator>Vinay Keswani</dc:creator><dc:creator>Pushkar Dubey</dc:creator><dc:subject>handwritten text generation</dc:subject><dc:subject>generative adversarial networks</dc:subject><dc:subject>training instability</dc:subject><dc:subject>Fréchet Inception Distance</dc:subject><dc:subject>MNIST</dc:subject><dc:subject>image generation</dc:subject><dc:description xml:lang="en">Image synthesis is particularly important for applications that want to create realistic handwritten documents, which is why handwritten text generation is a critical area within its domain. Even with today's highly advanced technology, generating diverse and accurate representations of human handwriting is still a tough problem because of the variability in style. In this study, we tackle the problem of instability during the training phase of generative adversarial networks (GANs) for generating handwritten text images. Using the MNIST dataset, which includes 60,000 training and 10,000 test images of handwritten digits, we trained a GAN model to generate synthetic handwritten images. The methodology involves optimizing both the generator and discriminator using adversarial training, binary cross-entropy loss, as well as the optimizer Adam. A brand-new decaying learning rate schedule was introduced to speed up convergence. Performance was evaluated using the Fréchet inception distance (FID) metric. The results show that this model effectively generated high-quality synthetic images of handwritten digits, which resembled real data closely in the face of it all and also that there was a steady reduction in FID scores across epochs indicating improved performance.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2025-05-02</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v14i3.9190</dc:identifier><dc:identifier>10.11591/eei.v14i3.9190</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 14 No 3 (2025); 2370-2379</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/9190/4252</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>