Generative Adversarial Networks for Image-to-Image Translation
- 1st Edition - June 22, 2021
- Imprint: Academic Press
- Editors: Arun Solanki, Anand Nayyar, Mohd Naved
- Language: English
- Paperback ISBN:9 7 8 - 0 - 1 2 - 8 2 3 5 1 9 - 5
- eBook ISBN:9 7 8 - 0 - 1 2 - 8 2 3 6 1 3 - 0
Generative Adversarial Networks (GAN) have started a revolution in Deep Learning, and today GAN is one of the most researched topics in Artificial Intelligence. Generative Ad… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteGenerative Adversarial Networks (GAN) have started a revolution in Deep Learning, and today GAN is one of the most researched topics in Artificial Intelligence. Generative Adversarial Networks for Image-to-Image Translation provides a comprehensive overview of the GAN (Generative Adversarial Network) concept starting from the original GAN network to various GAN-based systems such as Deep Convolutional GANs (DCGANs), Conditional GANs (cGANs), StackGAN, Wasserstein GANs (WGAN), cyclical GANs, and many more. The book also provides readers with detailed real-world applications and common projects built using the GAN system with respective Python code. A typical GAN system consists of two neural networks, i.e., generator and discriminator. Both of these networks contest with each other, similar to game theory. The generator is responsible for generating quality images that should resemble ground truth, and the discriminator is accountable for identifying whether the generated image is a real image or a fake image generated by the generator. Being one of the unsupervised learning-based architectures, GAN is a preferred method in cases where labeled data is not available. GAN can generate high-quality images, images of human faces developed from several sketches, convert images from one domain to another, enhance images, combine an image with the style of another image, change the appearance of a human face image to show the effects in the progression of aging, generate images from text, and many more applications. GAN is helpful in generating output very close to the output generated by humans in a fraction of second, and it can efficiently produce high-quality music, speech, and images.
- Introduces the concept of Generative Adversarial Networks (GAN), including the basics of Generative Modelling, Deep Learning, Autoencoders, and advanced topics in GAN
- Demonstrates GANs for a wide variety of applications, including image generation, Big Data and data analytics, cloud computing, digital transformation, E-Commerce, and Artistic Neural Networks
- Includes a wide variety of biomedical and scientific applications, including unsupervised learning, natural language processing, pattern recognition, image and video processing, and disease diagnosis
- Provides a robust set of methods that will help readers to appropriately and judiciously use the suitable GANs for their applications
Biomedical Engineers and researchers in biomedical engineering, applied informatics, Artificial Intelligence, and data science. Students and researchers in data analytics, image processing, as well as computer scientists
- Cover image
- Title page
- Table of Contents
- Copyright
- Contributors
- Chapter 1: Super-resolution-based GAN for image processing: Recent advances and future trends
- Abstract
- 1.1: Introduction
- 1.2: Background study
- 1.3: SR-GAN model for image processing
- 1.4: Case study
- 1.5: Open issues and challenges
- 1.6: Conclusion and future scope
- Chapter 2: GAN models in natural language processing and image translation
- Abstract
- 2.1: Introduction
- 2.2: Basic GAN model classification based on learning
- 2.3: GANs in natural language processing
- 2.4: GANs in image generation and translation
- 2.5: Evaluation metrics
- 2.6: Tools and languages used for GAN research
- 2.7: Open challenges for future research
- 2.8: Conclusion
- Chapter 3: Generative adversarial networks and their variants
- Abstract
- 3.1: Introduction of generative adversarial network (GAN)
- 3.2: Related work
- 3.3: Deep-learning methods
- 3.4: Variants of GAN
- 3.5: Applications of GAN
- 3.6: Conclusion
- Chapter 4: Comparative analysis of filtering methods in fuzzy C-means: Environment for DICOM image segmentation
- Abstract
- Acknowledgment
- 4.1: Introduction
- 4.2: Related works
- 4.3: Methodology
- 4.4: Experimental analysis
- 4.5: Performance analysis
- 4.6: Results and discussion
- 4.7: Conclusion
- Chapter 5: A review of the techniques of images using GAN
- Abstract
- 5.1: Introduction to GANs
- 5.2: GAN architectures
- 5.3: Discussion on research gaps
- 5.4: GAN applications
- 5.5: Conclusion
- Chapter 6: A review of techniques to detect the GAN-generated fake images
- Abstract
- 6.1: Introduction
- 6.2: DeepFake
- 6.3: DeepFake challenges
- 6.4: GAN-based techniques for generating DeepFake
- 6.5: Artificial intelligence-based methods to detect DeepFakes
- 6.6: Comparative study of artificial intelligence-based techniques to detect the face manipulation in GAN-generated fake images
- 6.7: Legal and ethical considerations
- 6.8: Conclusion and future scope
- Chapter 7: Synthesis of respiratory signals using conditional generative adversarial networks from scalogram representation
- Abstract
- 7.1: Introduction
- 7.2: Related work
- 7.3: GAN for signal synthesis
- 7.4: Results and discussion
- 7.5: Conclusion and future scope
- Chapter 8: Visual similarity-based fashion recommendation system
- Abstract
- 8.1: Introduction
- 8.2: Related works
- 8.3: Fashion recommendation system
- 8.4: Experiments and results
- 8.5: Conclusion and future works
- Chapter 9: Deep learning-based vegetation index estimation
- Abstract
- Acknowledgments
- 9.1: Introduction
- 9.2: Related work
- 9.3: Proposed approach
- 9.4: Results and discussions
- 9.5: Conclusions
- Chapter 10: Image generation using generative adversarial networks
- Abstract
- 10.1: Introduction to deep learning
- 10.2: Introduction to GAN
- 10.3: Applications
- 10.4: Future of GANs
- Chapter 11: Generative adversarial networks for histopathology staining
- Abstract
- 11.1: Introduction
- 11.2: Generative adversarial networks
- 11.3: The image-to-image translational problem
- 11.4: Histology and medical imaging
- 11.5: Network architecture and dataset
- 11.6: Results and discussions
- 11.7: Conclusions
- Appendix: Network architectures
- Chapter 12: Analysis of false data detection rate in generative adversarial networks using recurrent neural network
- Abstract
- 12.1: Introduction
- 12.2: Related works
- 12.3: Methods
- 12.4: GAN-RNN architecture
- 12.5: Performance evaluation
- 12.6: Conclusions
- Chapter 13: WGGAN: A wavelet-guided generative adversarial network for thermal image translation
- Abstract
- Acknowledgment
- 13.1: Introduction
- 13.2: Related work
- 13.3: Wavelet-guided generative adversarial network
- 13.4: Experiments
- 13.5: Conclusion
- Chapter 14: Generative adversarial network for video analytics
- Abstract
- 14.1: Introduction
- 14.2: Building blocks of GAN
- 14.3: GAN variations for video analytics
- 14.4: Discussion
- 14.5: Conclusion
- Chapter 15: Multimodal reconstruction of retinal images over unpaired datasets using cyclical generative adversarial networks
- Abstract
- 15.1: Introduction
- 15.2: Related research
- 15.3: Multimodal reconstruction of retinal images
- 15.4: Experiments and results
- 15.5: Discussion and conclusions
- Chapter 16: Generative adversarial network for video anomaly detection
- Abstract
- 16.1: Introduction
- 16.2: Literature review
- 16.3: Training a generative adversarial network
- 16.4: Experimental results
- 16.5: Summary
- Index
- Edition: 1
- Published: June 22, 2021
- No. of pages (Paperback): 444
- No. of pages (eBook): 444
- Imprint: Academic Press
- Language: English
- Paperback ISBN: 9780128235195
- eBook ISBN: 9780128236130
AS
Arun Solanki
Dr. Arun Solanki is Assistant Professor in the Department of Computer Science and Engineering, Gautam Buddha University, Greater Noida, India. He received his Ph.D. in Computer Science and Engineering from Gautam Buddha University. He has supervised more than 60 M.Tech. Dissertations under his guidance. His research interests span Expert System, Machine Learning, and Search Engines. Dr. Solanki is an Associate Editor of the
International Journal of Web-Based Learning and Teaching Technologies from IGI Global. He has been a Guest Editor for special issues of Recent Patents on Computer Science, from Bentham Science Publishers. Dr. Solanki is the editor of the books Green Building Management and Smart Automation and Handbook of Emerging Trends and Applications of Machine Learning, both from IGI Global.
Affiliations and expertise
Assistant Professor, Department of Computer Science and Engineering, Gautam Buddha University, Greater Noida, IndiaAN
Anand Nayyar
Dr. Anand Nayyar received his Ph.D (Computer Science) from Desh Bhagat University in 2017 in Wireless Sensor Networks and Swarm Intelligence. He is currently working in Graduate School, Faculty of Information Technology- Duy Tan University, Vietnam. He has published numerous research papers in various high-impact journals and holds 10 Australian patents and 1 Indian Design to his credit in the area of Wireless Communications, Artificial Intelligence, IoT and Image Processing.
Affiliations and expertise
Professor, Scientist, Vice-Chairman (Research) and Director at IoT and Intelligent Systems Lab, Duy Tan University, VietnamMN
Mohd Naved
Dr. Mohd Naved is an Associate Professor at Jaipuria Institute of Management in Noida, India, with over a decade of experience in Business Analytics, Data Science, and Artificial Intelligence. His research focuses on the applications of business analytics, data science, and artificial intelligence across various industries.
Affiliations and expertise
Associate Professor, Jaipuria Institute of Management, IndiaRead Generative Adversarial Networks for Image-to-Image Translation on ScienceDirect