Neural Style Transfer for Information Systems Theory Using Images and Videos

Ravi Uyyala (), Neha Krishna Karampuri, Sai Praveena Karnati and Premkumar Chithaluru ()
Additional contact information
Ravi Uyyala: Chaitanya Bharathi Institute of Technology
Neha Krishna Karampuri: Chaitanya Bharathi Institute of Technology
Sai Praveena Karnati: Chaitanya Bharathi Institute of Technology
Premkumar Chithaluru: Mahatma Gandhi Institute of Technology, (MGIT)

Chapter 11 in Leveraging Emerging Technologies and Analytics for Empowering Humanity, Vol. 1, 2025, pp 211-228 from Springer

Abstract: Abstract Neural Style Transfer (NST) stands at the forefront of innovation in the intersection of computer vision and artistic expression, providing a potent technique to elevate ordinary images and videos into captivating visual experiences. This project serves as an exploration into the amalgamation of neural networks and artistic aesthetics, utilizing NST to transcend the conventional boundaries of image processing and artistic creation.NST harnesses the power of deep convolutional neural networks, exemplified by architectures like VGG19. Through a sophisticated interplay of content and style loss functions, NST achieves the remarkable feat of disentangling and recombining content from one source image with the artistic style derived from another. This transformative process yields novel and visually striking compositions that seamlessly merge the content of an image or video frame with the distinctive style of renowned artworks or unique aesthetics.In the context of this project, we implement NST for both images and videos, showcasing its versatility and its potential to enrich visual storytelling across diverse domains, ranging from filmmaking to content creation. By integrating deep learning with artistic expression, this approach opens new creative avenues for professionals and enthusiasts alike.The technical intricacies of the NST process are examined in detail within this project. Special emphasis is placed on the role of convolutional neural networks in extracting content and style features, unraveling the underlying mechanisms that enable the transformation of mundane visuals into the extraordinary. The results of this exploration not only showcase the current potential of neural networks in solving the challenges of artistic style transfer but also offer a glimpse into the exciting possibilities that this technology holds for the future of visual content creation. NST emerges not merely as a tool for stylizing images but as a catalyst for redefining the very essence of visual storytelling and artistic innovation.

Keywords: Neural style transfer; Convolutional neural network; Artificial neural network; Visual geometry group; Style transfer transformer framework (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prbchp:978-981-96-2548-2_11

Ordering information: This item can be ordered from
http://www.springer.com/9789819625482

DOI: 10.1007/978-981-96-2548-2_11

Access Statistics for this chapter

More chapters in Springer Proceedings in Business and Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().