Abstract

Art is a variety of human activities that include the production of visual, auditory, or performing objects that express the creativity, creative concepts, or technological abilities of the artist, intended primarily for their beauty or emotional power to be appreciated. The renaissance of historic and forgotten art has been made possible by modern developments in Artificial Intelligence. Techniques for Computer Vision have long been related to such arts. Style Transfer using Neural Networks refers to optimization techniques, where a content image and a style image are taken and blended such that it feels like the content image is reconstructed in the style image color palette. This paper implements the Style Transfer using three different Neural Networks in form of an application that is accessible to the general population thereby reviving interest in lost art styles.

References

• Docker - a set of platform as a service products that use os-level virtualization to deliver software in packages called containers. https://www.docker.com/. Accessed: 2020- 03-11.
• Fastapi - a modern, fast (high-performance), web framework for building apis with python 3.6+ based on standard python type hints. https://fastapi.tiangolo.com/. Accessed: 2020-03-11.
• Git - a free and open source distributed version control system. https://git-scm.com/. Accessed: 2020-03-11.
• Gunicorn - a python web server gateway interface http server. https://gunicorn.org/. Accessed: 2020-03-11.
• Material ui - a popular react ui framework. https:// material-ui.com/. Accessed: 2020-03-11.
• React - a javascript library for building user interfaces. https://reactjs.org/. Accessed: 2020-03-11.
• Tensorflow - a free and open-source software library for machine learning. https://www.tensorflow.org/. Accessed: 2020-03-11.
• Uvicorn - a lightning-fast asgi server implementation, using uvloop and httptools. https://www.uvicorn.org/. Accessed: 2020-03-11.
• Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. A neural algorithm of artistic style. CoRR, abs/1508.06576, 2015.
• Golnaz Ghiasi, Honglak Lee, Manjunath Kudlur, Vincent Dumoulin, and Jonathon Shlens. Exploring the structure of a real-time, arbitrary neural artistic stylization network. CoRR, abs/1705.06830, 2017.
• C. Hu, Y. Ding, and Y. Li. Image style transfer based on generative adversarial network. In 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), volume 1, pages 2098–2102, 2020.
• Mark Sandler, Andrew G. Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation. CoRR, abs/1801.04381, 2018.
• Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition, 2015.
• Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. Rethinking the inception architecture for computer vision. CoRR, abs/1512.00567, 2015.
• Amogh G. Warkhandkar, Baasit Sharief, and Omkar B. Bhambure. Measuring performance of generative adversarial networks on devanagari script. International Journal of Computer Applications, 176(33):5–9, Jun 2020.
• Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. Unpaired image-to-image translation using cycleconsistent adversarial networks. CoRR, abs/1703.10593, 2017.