A comparative study of car image generation quality using DCGAN and VSGAN
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022.
| Main Authors: | , , , , |
|---|---|
| 其他作者: | |
| 格式: | Thesis |
| 語言: | en_US |
| 出版: |
Brac University
2022
|
| 主題: | |
| 在線閱讀: | http://hdl.handle.net/10361/17644 |
| id |
10361-17644 |
|---|---|
| record_format |
dspace |
| spelling |
10361-176442022-12-13T21:01:45Z A comparative study of car image generation quality using DCGAN and VSGAN Shayer, Mirza Ahmad Anjum, Nafisha Mim, Sushana Islam Chowdhury, Md. Abu Sajid Preoshi, Noshin Nanjiba Islam Mostakim, Moin Department of Computer Science and Engineering, Brac University Image generation GAN CGAN DCGAN VSGAN WGAN WGANGP Epochs Training Testing K Nearest Neighbors Regression Random Forest Classifier Image processing--Digital techniques This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (pages 47-50). In today’s modern society, image generation (synthesis) has a great number of uses in various tasks. Image generation is used in crime forensics, improving image quality and generating better images. In 2014, a scientific breakthrough occurred in the machine learning community when Ian Goodfellow and his colleagues introduced the GAN (Generative Adversarial Network). Ever since then, GANs have become a more popular concept in the scientific community. Even today, GANs are being used, utilized and upgraded. This thesis is a comparative study of two GANs used for generating images of cars- DC-GAN (Deep Convolution) and VS-GAN (Vehicle Synthesis). The study will determine which of the two is better suited to generate high quality images of cars. We will train both GANs using the same dataset. The dataset consists of about 16185 Google images of random cars, 8144 for training and another 8041 for testing. The dataset is already preprocessed and split. We will compare the GANs training times, losses, accuracies and pictures generated, showing how well they perform. We will run all the GANs for 40 epochs in both training and testing. We will compare the CGAN, DCGAN, VSGAN, WGAN and WGAN-GP, to see which performs the best. We have used K-Nearest Neighbors, Regression and Random Forest Classifier to calculate the accuracies of all the GANs. We have displayed the results in tabular and graphical formats. We believe this will improve GAN research by providing an excellent comparison between the GANs and determine which is better suited for the given task. We also hope to improve the models further in the future and make an even more in depth comparison between the GAN architectures. Mirza Ahmad Shayer Nafisha Anjum Sushana Islam Mim Md. Abu Sajid Chowdhury Noshin Nanjiba Islam Preoshi B. Computer Science and Engineering 2022-12-13T05:15:14Z 2022-12-13T05:15:14Z 2022 2022-05 Thesis ID: 18101496 ID: 18301217 ID: 18101579 ID: 18101013 ID: 18101002 http://hdl.handle.net/10361/17644 en_US Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 50 Pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
en_US |
| topic |
Image generation GAN CGAN DCGAN VSGAN WGAN WGANGP Epochs Training Testing K Nearest Neighbors Regression Random Forest Classifier Image processing--Digital techniques |
| spellingShingle |
Image generation GAN CGAN DCGAN VSGAN WGAN WGANGP Epochs Training Testing K Nearest Neighbors Regression Random Forest Classifier Image processing--Digital techniques Shayer, Mirza Ahmad Anjum, Nafisha Mim, Sushana Islam Chowdhury, Md. Abu Sajid Preoshi, Noshin Nanjiba Islam A comparative study of car image generation quality using DCGAN and VSGAN |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022. |
| author2 |
Mostakim, Moin |
| author_facet |
Mostakim, Moin Shayer, Mirza Ahmad Anjum, Nafisha Mim, Sushana Islam Chowdhury, Md. Abu Sajid Preoshi, Noshin Nanjiba Islam |
| format |
Thesis |
| author |
Shayer, Mirza Ahmad Anjum, Nafisha Mim, Sushana Islam Chowdhury, Md. Abu Sajid Preoshi, Noshin Nanjiba Islam |
| author_sort |
Shayer, Mirza Ahmad |
| title |
A comparative study of car image generation quality using DCGAN and VSGAN |
| title_short |
A comparative study of car image generation quality using DCGAN and VSGAN |
| title_full |
A comparative study of car image generation quality using DCGAN and VSGAN |
| title_fullStr |
A comparative study of car image generation quality using DCGAN and VSGAN |
| title_full_unstemmed |
A comparative study of car image generation quality using DCGAN and VSGAN |
| title_sort |
comparative study of car image generation quality using dcgan and vsgan |
| publisher |
Brac University |
| publishDate |
2022 |
| url |
http://hdl.handle.net/10361/17644 |
| work_keys_str_mv |
AT shayermirzaahmad acomparativestudyofcarimagegenerationqualityusingdcganandvsgan AT anjumnafisha acomparativestudyofcarimagegenerationqualityusingdcganandvsgan AT mimsushanaislam acomparativestudyofcarimagegenerationqualityusingdcganandvsgan AT chowdhurymdabusajid acomparativestudyofcarimagegenerationqualityusingdcganandvsgan AT preoshinoshinnanjibaislam acomparativestudyofcarimagegenerationqualityusingdcganandvsgan AT shayermirzaahmad comparativestudyofcarimagegenerationqualityusingdcganandvsgan AT anjumnafisha comparativestudyofcarimagegenerationqualityusingdcganandvsgan AT mimsushanaislam comparativestudyofcarimagegenerationqualityusingdcganandvsgan AT chowdhurymdabusajid comparativestudyofcarimagegenerationqualityusingdcganandvsgan AT preoshinoshinnanjibaislam comparativestudyofcarimagegenerationqualityusingdcganandvsgan |
| _version_ |
1814308975674392576 |