An examination of synthetic images produced with DCGAN according to the size of data and epoch
In recent years, the popular network of adversarial networks has increased in studies for computer vision. The lack of data used in the studies and the lack of good training for the resulting model draw attention to techniques such as data enhancement and synthetic data generation. In this article,...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Firat University
2023-02-01
|
| Series: | Firat University Journal of Experimental and Computational Engineering |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/tr/download/article-file/2950765 |
| _version_ | 1797628098042134528 |
|---|---|
| author | Fatih Özyurt Canan Koç |
| author_facet | Fatih Özyurt Canan Koç |
| author_sort | Fatih Özyurt |
| collection | DOAJ |
| description | In recent years, the popular network of adversarial networks has increased in studies for computer vision. The lack of data used
in the studies and the lack of good training for the resulting model draw attention to techniques such as data enhancement and
synthetic data generation. In this article, synthetic data was produced using Generative Adversarial Networks (GANs). The data
in the dataset used consists of 10000 faces from the CelebA dataset available online. The impact of the increase in the number
of data on fake images created by DCGAN, one of the GANs, is the main topic of the article. In the study, the data is divided
into two parts. In the first study, fake data were generated from 5000 data, and in the next study, fake data images were forged
using all of the data meaning 10000 data. The result was found that the number of data and the increase in epoch were accurately
proportional to the success of the fraudulent images created. |
| first_indexed | 2024-03-11T10:33:40Z |
| format | Article |
| id | doaj.art-866c9c284d0845c18324fdeaf53f9932 |
| institution | Directory Open Access Journal |
| issn | 2822-2881 |
| language | English |
| last_indexed | 2024-03-11T10:33:40Z |
| publishDate | 2023-02-01 |
| publisher | Firat University |
| record_format | Article |
| series | Firat University Journal of Experimental and Computational Engineering |
| spelling | doaj.art-866c9c284d0845c18324fdeaf53f99322023-11-14T11:36:56ZengFirat UniversityFirat University Journal of Experimental and Computational Engineering2822-28812023-02-0121323710.5505/fujece.2023.698851769An examination of synthetic images produced with DCGAN according to the size of data and epochFatih Özyurt0Canan Koç1FIRAT ÜNİVERSİTESİFIRAT ÜNİVERSİTESİIn recent years, the popular network of adversarial networks has increased in studies for computer vision. The lack of data used in the studies and the lack of good training for the resulting model draw attention to techniques such as data enhancement and synthetic data generation. In this article, synthetic data was produced using Generative Adversarial Networks (GANs). The data in the dataset used consists of 10000 faces from the CelebA dataset available online. The impact of the increase in the number of data on fake images created by DCGAN, one of the GANs, is the main topic of the article. In the study, the data is divided into two parts. In the first study, fake data were generated from 5000 data, and in the next study, fake data images were forged using all of the data meaning 10000 data. The result was found that the number of data and the increase in epoch were accurately proportional to the success of the fraudulent images created.https://dergipark.org.tr/tr/download/article-file/2950765çekişmeli üretici ağlarsentetik veriüretici modelgenerative adversarial networkssynthetic datagenerative modelçekişmeli üretici ağlarsentetik veriüretici model |
| spellingShingle | Fatih Özyurt Canan Koç An examination of synthetic images produced with DCGAN according to the size of data and epoch Firat University Journal of Experimental and Computational Engineering çekişmeli üretici ağlar sentetik veri üretici model generative adversarial networks synthetic data generative model çekişmeli üretici ağlar sentetik veri üretici model |
| title | An examination of synthetic images produced with DCGAN according to the size of data and epoch |
| title_full | An examination of synthetic images produced with DCGAN according to the size of data and epoch |
| title_fullStr | An examination of synthetic images produced with DCGAN according to the size of data and epoch |
| title_full_unstemmed | An examination of synthetic images produced with DCGAN according to the size of data and epoch |
| title_short | An examination of synthetic images produced with DCGAN according to the size of data and epoch |
| title_sort | examination of synthetic images produced with dcgan according to the size of data and epoch |
| topic | çekişmeli üretici ağlar sentetik veri üretici model generative adversarial networks synthetic data generative model çekişmeli üretici ağlar sentetik veri üretici model |
| url | https://dergipark.org.tr/tr/download/article-file/2950765 |
| work_keys_str_mv | AT fatihozyurt anexaminationofsyntheticimagesproducedwithdcganaccordingtothesizeofdataandepoch AT canankoc anexaminationofsyntheticimagesproducedwithdcganaccordingtothesizeofdataandepoch AT fatihozyurt examinationofsyntheticimagesproducedwithdcganaccordingtothesizeofdataandepoch AT canankoc examinationofsyntheticimagesproducedwithdcganaccordingtothesizeofdataandepoch |