DEEP LEARNING TECHNIQUES OF ARTISTIC IMAGE MODIFICATION
DOI:
https://doi.org/10.24867/12BE42KecaKeywords:
Style transfer, Deep Dream, convolutional neural networksAbstract
This paper describes the methods of artistic image transformation. The methods rely on convolutional neural networks trained for image recognition to differentiate between image style and content. The paper describes iterative algorithms such as style transfer and Deep Dream, as well as improvements of these original algorithms. The behavior of these algorithms is analyzed by experimenting with different parameter configurations. All algorithms were implemented using the Python programming language and Tensorflow package.
References
[1] L. A. Gatys, A. S. Ecker, M. Bethge, A Neural Algorithm of Artistic Style, 2015.
[2] Google AI Blog. 2015. Inceptionism: Going Deeper Into Neural Networks. [online] Available at: <https://ai.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html>
[3] K. Simonyan, A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recongition, 2015.
[4] L. A. Gatys, M. Berthge, A. Hertzmann, E. Shechtman, Preserving Color in Neural Artistic Style Transfer, 2016.
[5] TensorFlow. 2020. Deepdream | Tensorflow Core. [online] Available at: <https://www.tensorflow.org/tutorials/generative/deepdream>
[6] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Rethinking the Inception Architecture for Computer Vision, 2015.
[7] Olga Russakovsky*, Jia Deng*, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei. (* = equal contribution) ImageNet Large Scale Visual Recognition Challenge. IJCV, 2015.
[2] Google AI Blog. 2015. Inceptionism: Going Deeper Into Neural Networks. [online] Available at: <https://ai.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html>
[3] K. Simonyan, A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recongition, 2015.
[4] L. A. Gatys, M. Berthge, A. Hertzmann, E. Shechtman, Preserving Color in Neural Artistic Style Transfer, 2016.
[5] TensorFlow. 2020. Deepdream | Tensorflow Core. [online] Available at: <https://www.tensorflow.org/tutorials/generative/deepdream>
[6] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Rethinking the Inception Architecture for Computer Vision, 2015.
[7] Olga Russakovsky*, Jia Deng*, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei. (* = equal contribution) ImageNet Large Scale Visual Recognition Challenge. IJCV, 2015.
Downloads
Published
2021-03-09
Issue
Section
Electrotechnical and Computer Engineering
