Abstract
A technique called neural style transfer is an effective method for generating artistic images based on a deep learning technique. It can extract a mood of a specific painting and blends it with a different image. The original method, however, needs a high-performance computer to get an output image within a practical response time since the neural style transfer involves heavily-loaded processing. To solve the problem, we develop a web-based image editing system enabling users to readily access the function only by using a mobile device with a standard web browser and a network connection. The proposed system allows the users to easily generating a wide variety of artistic images like logos and image clips using the neural style transfer anywhere they have a connection to the Internet. We implement the system as a web application and conduct some experiments to verify the effectiveness of the system. We elaborate the implementation method, experimental results, and observations in this paper.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414–2423 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, pp. 1–14 (2015)
Champandard, A.J.: Semantic style transfer and turning two-bit doodles into fine artworks. arXiv:1603.01768, pp. 1–7 (2016)
Luan, F., Paris, S., Shechtman, E., Bala, K.: Deep photo style transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6997–7005 (2016)
Goto, K., Nishino, H.: A method of neural style transfer for images with artistic characters. In: Proceedings of the 12th International Conference on Complex, Intelligent and Software Intensive Systems, pp. 911–920 (2018)
The MariaDB Foundation. https://mariadb.org/. Accessed Jan 2019
Miura, S., Nishino, H.: A practical colour scheme explorer for designers. Int. J. Space-Based Situated Comput. 7(3), 155–165 (2017)
Bianco, S., Celona, L., Napoletano, P., Schettini, R.: Predicting image aesthetics with deep learning. In: Proceedings of the 17th International Conference on Advanced Concepts for Intelligent Vision Systems, pp. 117–125 (2016)
Lu, X., Lin, Z., Jin, H., Yang, J., Wang, J.Z.: Rating image aesthetics using deep learning. IEEE Trans. Multimedia 17(11), 2021–2034 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Goto, K., Nishino, H. (2020). A Web-Based Artwork Editing System Empowered by Neural Style Transfer. In: Barolli, L., Takizawa, M., Xhafa, F., Enokido, T. (eds) Advanced Information Networking and Applications. AINA 2019. Advances in Intelligent Systems and Computing, vol 926. Springer, Cham. https://doi.org/10.1007/978-3-030-15032-7_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-15032-7_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-15031-0
Online ISBN: 978-3-030-15032-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)