Generating and compressing images from a large volume of discrete datasets using GANs along with different compression techniques and studying the results
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.
| المؤلفون الرئيسيون: | , , , , |
|---|---|
| مؤلفون آخرون: | |
| التنسيق: | أطروحة |
| اللغة: | English |
| منشور في: |
Brac University
2023
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | http://hdl.handle.net/10361/21794 |
| id |
10361-21794 |
|---|---|
| record_format |
dspace |
| spelling |
10361-217942023-10-12T21:05:11Z Generating and compressing images from a large volume of discrete datasets using GANs along with different compression techniques and studying the results Sajid, Mayeen Abedin Jisan, Md. Tanvir Mahtab Reza, Syeda Nowrin Jueb, Ashraf Mufidul Islam Meem, Tahmin Khandaker Mostakim, Moin Department of Computer Science and Engineering, Brac University GAN CGAN DCGAN Discriminator Image generation K Means clustering DCT Testing Compression Epochs Training Pillow Computer graphics Image processing--Digital techniques This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (pages 55-56). Image is among the most common and important factors in modern day research. From Image processing to Image synthesis all the aspects of image are necessary and have always been prioritized. For this we tried to incorporate a comparatively new process of image generation in our research, that is GAN. In this new era of technology GAN has gained a lot of popularity for generating new images and synthesizing old images. Our thesis is a study of two popular GANs that is CGAN and DCGAN where we came up with the working ability of both the GANs by analyzing its training and testing with the help of a large volume of discrete datasets. One of the datasets consists of almost 16000 cars images and the other dataset is of dogs images which contains almost 5000 dogs images. We have run both the DCGAN and CGAN for both the datasets with 50 epochs in training and testing. Moreover besides the use of GAN and comparing it we compared three different techniques of image compression which are Discrete Cosine Transform that is DCT, K-Means Clustering and the Pillow Library of Python. With the use of image compression tools, we can compress images fast and efficiently, resulting in a reduction in storage space while maintaining a minimal influence on picture quality. We compressed both the real images from our dataset and the fake generated images. After that we studied the results by comparing the compression percentage and differentiating the images quality. We believe that our research will provide an excellent comparison of the GANs and compression techniques which will help future researchers to understand which technique to use for optimum result. We hope to improve our models in the future and also incorporate both the image generation and compression to come up with better quality images using less memory space. It means that we will be able to achieve the greatest amount of clarity while taking up the least amount of space. Mayeen Abedin Sajid Md. Tanvir Mahtab Jisan Syeda Nowrin Reza Ashraf Mufidul Islam Jueb Tahmin Khandaker Meem B.Sc. in Computer Science 2023-10-12T10:48:58Z 2023-10-12T10:48:58Z ©2022 2022-09-22 Thesis ID 18101604 ID 18101378 ID 18101092 ID 18101466 ID 18101524 http://hdl.handle.net/10361/21794 en 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. 67 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
GAN CGAN DCGAN Discriminator Image generation K Means clustering DCT Testing Compression Epochs Training Pillow Computer graphics Image processing--Digital techniques |
| spellingShingle |
GAN CGAN DCGAN Discriminator Image generation K Means clustering DCT Testing Compression Epochs Training Pillow Computer graphics Image processing--Digital techniques Sajid, Mayeen Abedin Jisan, Md. Tanvir Mahtab Reza, Syeda Nowrin Jueb, Ashraf Mufidul Islam Meem, Tahmin Khandaker Generating and compressing images from a large volume of discrete datasets using GANs along with different compression techniques and studying the results |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. |
| author2 |
Mostakim, Moin |
| author_facet |
Mostakim, Moin Sajid, Mayeen Abedin Jisan, Md. Tanvir Mahtab Reza, Syeda Nowrin Jueb, Ashraf Mufidul Islam Meem, Tahmin Khandaker |
| format |
Thesis |
| author |
Sajid, Mayeen Abedin Jisan, Md. Tanvir Mahtab Reza, Syeda Nowrin Jueb, Ashraf Mufidul Islam Meem, Tahmin Khandaker |
| author_sort |
Sajid, Mayeen Abedin |
| title |
Generating and compressing images from a large volume of discrete datasets using GANs along with different compression techniques and studying the results |
| title_short |
Generating and compressing images from a large volume of discrete datasets using GANs along with different compression techniques and studying the results |
| title_full |
Generating and compressing images from a large volume of discrete datasets using GANs along with different compression techniques and studying the results |
| title_fullStr |
Generating and compressing images from a large volume of discrete datasets using GANs along with different compression techniques and studying the results |
| title_full_unstemmed |
Generating and compressing images from a large volume of discrete datasets using GANs along with different compression techniques and studying the results |
| title_sort |
generating and compressing images from a large volume of discrete datasets using gans along with different compression techniques and studying the results |
| publisher |
Brac University |
| publishDate |
2023 |
| url |
http://hdl.handle.net/10361/21794 |
| work_keys_str_mv |
AT sajidmayeenabedin generatingandcompressingimagesfromalargevolumeofdiscretedatasetsusinggansalongwithdifferentcompressiontechniquesandstudyingtheresults AT jisanmdtanvirmahtab generatingandcompressingimagesfromalargevolumeofdiscretedatasetsusinggansalongwithdifferentcompressiontechniquesandstudyingtheresults AT rezasyedanowrin generatingandcompressingimagesfromalargevolumeofdiscretedatasetsusinggansalongwithdifferentcompressiontechniquesandstudyingtheresults AT juebashrafmufidulislam generatingandcompressingimagesfromalargevolumeofdiscretedatasetsusinggansalongwithdifferentcompressiontechniquesandstudyingtheresults AT meemtahminkhandaker generatingandcompressingimagesfromalargevolumeofdiscretedatasetsusinggansalongwithdifferentcompressiontechniquesandstudyingtheresults |
| _version_ |
1814308840502460416 |