Abstract
GANs are a very interesting emerging domain. Implementation of the Neural style transfer technique can be done using particular types of these GANs. In this technique, a particular art style is superimposed over a certain image, resulting in the input image looking like a painting in the same style. A similar result can be achieved through manually mixing the input image and a painting using rudimentary image manipulation techniques. The goal of this paper is to analyse the difference between these outputs using a variety of techniques such as Discrete Cosine Transform and Fourier Transform along with others, to observe the amount of difference in the techniques. We conclude with a discussion on how the manually mixed image can be tweaked to most closely resemble the GAN output.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gatys LA, Ecker AS, Bethge M (2015) A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576
Goodfellow I et al (2014) Generative adversarial nets. Adv Neural Inf Process Syst 27
Zhu J-Y et al (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE international conference on computer vision
Coup S, Vetrova V, Frank E, Tappenden R (2019) Domain specific transfer learning using image mixing and stochastic image selection. Presented at the the sixth workshop on fine-grained visual categorization (FGVC6), computer vision and pattern recognition conference (EVPR 2019), Long Beach, CA
Gatys LA, Ecker AS, Bethge M (2016) Image style transfer using convolutional neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition
Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434
Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
Karras T et al (2020) Analyzing and improving the image quality of stylegan. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
Zhang L, Wen T, Shi J (2020) Deep image blending. In: IEEE/CVF winter conference, applications of computer vision (WACV), pp 231–240
Zeng S, Hu H, Zhange J, Huang K (2019) GP-GAN towards realistic high resolution image blending. In: 27th ACM international conference on multimedia
Tmenova O, Martin R (2019) CycleGAN for style transfer in X-ray angiography published in springer
Kaggle Team “I’m Something of a Painter Myself” version 1. https://www.kaggle.com/c/gan-getting-started/data
Pandian AP (2021) Review on image recoloring methods for efficient naturalness by coloring data modeling methods for low visual deficiency. J Arti Intell 3(3):169–183
Drori I, Cohen-Or D, Yeshurun H (2003) Example-based style synthesis. 2003 IEEE computer society conference on computer vision and pattern recognition, Proceedings, vol 2. IEEE
Darney PE, Jeena Jacob I (2021) Rain streaks removal in digital images by dictionary based sparsity process with MCA Estimation. J Innov Image Process 3:174–189
Gireesan G, Mathew LS (2019) Stratified meta structure based similarity measure in heterogeneous information networks for medical diagnosis. In: International conference on computational vision and bio inspired computing. Springer, Cham, pp 66–70
Mahajan AD, Chaudhary S (2019) Image context based similarity retrieval system. In: International conference on computational vision and bio inspired computing. Springer, Cham, , pp 1265–1272
Irfan S, Ghosh S (2019) Efficient ranking framework for information retrieval using similarity measure. In: International conference on computational vision and bio inspired computing. Springer, Cham, pp 1344–1354
Rouse D, Hemami SS (2008) Understanding and simplifying the structural similarity metric. Proceedings international conference image process, pp 325328
Chen G, Yang C, Xie S (2006) Edge-based structural similarity for image quality assessment. Proceedings international conference acoustics. Speech Signal Process. pp. 14–19
Sara U, Akter M, Uddin MS (2019) Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study. Proc J Comput Commun 7(3)
Narwaria M, Lin W, McLoughlin IV, Emmanuel S, Chia L (2012) Fourier transform-based scalable image quality measure. IEEE Trans Image Process 21(8):3364–3377
Agarwal S, Girdhar N, Raghav H (2021) A novel neural model based framework for detection of GAN generated fake images. 2021 11th international conference on cloud computing, data science & engineering (Confluence), pp 46–51
Tomosada H, Kudo T, Fujisawa T, Ikehara M (2021) GAN-based image Deblurring using DCT loss with customized datasets. IEEE Access 9:135224–135233
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wyawahare, M., Ekbote, N., Pimperkhede, S., Deshpande, A., Bapat, P., Aphale, I. (2023). Comparison of Image Blending Using Cycle GAN and Traditional Approach. In: Ranganathan, G., Bestak, R., Fernando, X. (eds) Pervasive Computing and Social Networking. Lecture Notes in Networks and Systems, vol 475. Springer, Singapore. https://doi.org/10.1007/978-981-19-2840-6_44
Download citation
DOI: https://doi.org/10.1007/978-981-19-2840-6_44
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-2839-0
Online ISBN: 978-981-19-2840-6
eBook Packages: EngineeringEngineering (R0)