Performance Analysis of Cycle GAN in Photo to Portrait Transfiguration Using Deep Learning Optimizers
In the realm of computer vision, image transformations play a pivotal role across various domains such as healthcare, image enhancement, artist painting identification, genome sequencing, and more. While supervised learning demands a substantial volume of annotated images for training models, Cycle-...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10332183/ |
| _version_ | 1797392278824681472 |
|---|---|
| author | L. Lakshmi A. Naga Kalyani D. Krishna Madhuri Sirisha Potluri Geetika Silakari Pandey Shahid Ali Muhammad Ijaz Khan Fuad A. Awwad Emad A. A. Ismail |
| author_facet | L. Lakshmi A. Naga Kalyani D. Krishna Madhuri Sirisha Potluri Geetika Silakari Pandey Shahid Ali Muhammad Ijaz Khan Fuad A. Awwad Emad A. A. Ismail |
| author_sort | L. Lakshmi |
| collection | DOAJ |
| description | In the realm of computer vision, image transformations play a pivotal role across various domains such as healthcare, image enhancement, artist painting identification, genome sequencing, and more. While supervised learning demands a substantial volume of annotated images for training models, Cycle-GAN emerges as a potent solution for training models with fewer paired sources and target images in an unsupervised manner. This study introduces a novel system aimed at generating Monet-style paintings from realistic images, leveraging the Cycle-GAN methodology. Given the scarcity of Monet paintings, our system employs a combination of generator and discriminator neural networks to produce new Monet-style artworks. The model is trained using Cycle-GAN in conjunction with deep learning optimizers like RMSprop, ADAM, and SGD. The training dataset, Monet2Photo, comprises two distinct image categories: Monet paintings (300 samples) and natural photographs (7028 samples). The Monet-style images are utilized for training the model, while the raw photo images serve as the test set. Notably, the proposed model exhibits commendable performance, particularly when utilizing the SGD optimizer, as evidenced by favorable outcomes in terms of generator and discriminator losses. |
| first_indexed | 2024-03-08T23:44:57Z |
| format | Article |
| id | doaj.art-a57cb94a0a0e4a04a366cae0428661ec |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T23:44:57Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a57cb94a0a0e4a04a366cae0428661ec2023-12-14T00:01:30ZengIEEEIEEE Access2169-35362023-01-011113654113655110.1109/ACCESS.2023.333743010332183Performance Analysis of Cycle GAN in Photo to Portrait Transfiguration Using Deep Learning OptimizersL. Lakshmi0A. Naga Kalyani1D. Krishna Madhuri2Sirisha Potluri3Geetika Silakari Pandey4Shahid Ali5https://orcid.org/0009-0007-0731-0799Muhammad Ijaz Khan6Fuad A. Awwad7Emad A. A. Ismail8Department of DS and AI, Faculty of Science and Technology (IcfaiTech), ICFAI Foundation for Higher Education, Hyderabad, IndiaDepartment of CSE (AI and ML), BVRIT Hyderabad College of Engineering for Women, Hyderabad, IndiaDepartment of DS and AI, Faculty of Science and Technology (IcfaiTech), ICFAI Foundation for Higher Education, Hyderabad, IndiaDepartment of CSE, Faculty of Science and Technology (IcfaiTech), ICFAI Foundation for Higher Education, Hyderabad, IndiaDepartment of CSE (AI and ML), BVRIT Hyderabad College of Engineering for Women, Hyderabad, IndiaDept. of Electronics Engineering, Peking University, Beijing, ChinaDept. of Mathematics and Statistics, Riphah International University, Islamabad, PakistanDept. of Quantitative Analysis, College of Business Administration, King Saud University, Riyadh, Saudi ArabiaDept. of Quantitative Analysis, College of Business Administration, King Saud University, Riyadh, Saudi ArabiaIn the realm of computer vision, image transformations play a pivotal role across various domains such as healthcare, image enhancement, artist painting identification, genome sequencing, and more. While supervised learning demands a substantial volume of annotated images for training models, Cycle-GAN emerges as a potent solution for training models with fewer paired sources and target images in an unsupervised manner. This study introduces a novel system aimed at generating Monet-style paintings from realistic images, leveraging the Cycle-GAN methodology. Given the scarcity of Monet paintings, our system employs a combination of generator and discriminator neural networks to produce new Monet-style artworks. The model is trained using Cycle-GAN in conjunction with deep learning optimizers like RMSprop, ADAM, and SGD. The training dataset, Monet2Photo, comprises two distinct image categories: Monet paintings (300 samples) and natural photographs (7028 samples). The Monet-style images are utilized for training the model, while the raw photo images serve as the test set. Notably, the proposed model exhibits commendable performance, particularly when utilizing the SGD optimizer, as evidenced by favorable outcomes in terms of generator and discriminator losses.https://ieeexplore.ieee.org/document/10332183/Cycle-GANgeneratordiscriminatorobject transfigurationunsupervised learninggenerative adversarial networks |
| spellingShingle | L. Lakshmi A. Naga Kalyani D. Krishna Madhuri Sirisha Potluri Geetika Silakari Pandey Shahid Ali Muhammad Ijaz Khan Fuad A. Awwad Emad A. A. Ismail Performance Analysis of Cycle GAN in Photo to Portrait Transfiguration Using Deep Learning Optimizers IEEE Access Cycle-GAN generator discriminator object transfiguration unsupervised learning generative adversarial networks |
| title | Performance Analysis of Cycle GAN in Photo to Portrait Transfiguration Using Deep Learning Optimizers |
| title_full | Performance Analysis of Cycle GAN in Photo to Portrait Transfiguration Using Deep Learning Optimizers |
| title_fullStr | Performance Analysis of Cycle GAN in Photo to Portrait Transfiguration Using Deep Learning Optimizers |
| title_full_unstemmed | Performance Analysis of Cycle GAN in Photo to Portrait Transfiguration Using Deep Learning Optimizers |
| title_short | Performance Analysis of Cycle GAN in Photo to Portrait Transfiguration Using Deep Learning Optimizers |
| title_sort | performance analysis of cycle gan in photo to portrait transfiguration using deep learning optimizers |
| topic | Cycle-GAN generator discriminator object transfiguration unsupervised learning generative adversarial networks |
| url | https://ieeexplore.ieee.org/document/10332183/ |
| work_keys_str_mv | AT llakshmi performanceanalysisofcycleganinphototoportraittransfigurationusingdeeplearningoptimizers AT anagakalyani performanceanalysisofcycleganinphototoportraittransfigurationusingdeeplearningoptimizers AT dkrishnamadhuri performanceanalysisofcycleganinphototoportraittransfigurationusingdeeplearningoptimizers AT sirishapotluri performanceanalysisofcycleganinphototoportraittransfigurationusingdeeplearningoptimizers AT geetikasilakaripandey performanceanalysisofcycleganinphototoportraittransfigurationusingdeeplearningoptimizers AT shahidali performanceanalysisofcycleganinphototoportraittransfigurationusingdeeplearningoptimizers AT muhammadijazkhan performanceanalysisofcycleganinphototoportraittransfigurationusingdeeplearningoptimizers AT fuadaawwad performanceanalysisofcycleganinphototoportraittransfigurationusingdeeplearningoptimizers AT emadaaismail performanceanalysisofcycleganinphototoportraittransfigurationusingdeeplearningoptimizers |