Abstract
An image is identical to a thousand words. Each image pulls the watcher in, to an alternate time and spot making him experience a heap of feelings. They ll in as a path through a world of fond memories. However, consider the possibility that these photographs were harmed or have undesirable objects. To re-establish these photographs by elim-inating damages such as scratches, haziness and overlaid content or il-lustrations, we can utilize a procedure called Image Inpainting. Image inpainting is the procedure of reestablishing the harmed and missing pieces of a picture with the objective of introducing the picture as it was initially envisioned. The extent of our strategy ranges from expulsion of undesirable articles from the picture to reproducing the deteriorated and obscured out parts of the picture. Further, it could be utilized to improve quality of the pictures (for example, the ones capturing criminal activ-ities and their perpetrators). In our paper, we present a profound deep learning procedure to accomplish the above objectives. A pix2pix Gen-erative Adversarial Network is being utilized here with various encoders and decoders which extract the essential highlights of the picture and afterwards recreate it without any fuss.
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
Criminisi, A., Perez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE Trans. Image Process. 13(9), 1200–1212 (2004)
Isola, P., et al.: Image-to-image translation with conditional adversarial net-works. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Jia, J., Tang, C.-K.: Image repairing: robust image synthesis by adaptive nd tensor voting. In: 2003 IEEE Computer Society Conference on Computer Vi-sion and Pattern Recognition, Proceedings, vol. 1. IEEE (2003)
Fawzi, A., et al.: Image inpainting through neural networks hallucinations. In: 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP). IEEE (2016)
Kim, C., et al.: Diminishing unwanted objects based on object detection using deep learning and image inpainting. In: 2018 International Workshop on Advanced Image Technology (IWAIT). IEEE (2018)
Redmon, J., et al.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Cai, N., et al.: Blind inpainting using the fully convolutional neural network. Vis. Comput. 33(2), 249–261 (2017)
Yu, J., et al.: Generative image inpainting with contextual attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Hsu, C., Chen, F., Wang, G.: High-resolution image inpainting through multiple deep networks. In: 2017 International Conference on Vision, Image and Signal Processing (ICVISP). IEEE (2017).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Suraj, K.A., Swamy, S.H., Shetty, S.S., Jayashree, R. (2021). A Deep Learning Technique for Image Inpainting with GANs. In: Gunjan, V.K., Zurada, J.M. (eds) Modern Approaches in Machine Learning and Cognitive Science: A Walkthrough. Studies in Computational Intelligence, vol 956. Springer, Cham. https://doi.org/10.1007/978-3-030-68291-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-68291-0_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68290-3
Online ISBN: 978-3-030-68291-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)