A GAN Based Automatic Image Colourizer
Keywords:
Grayscale Images, Coloured Images, GAN, Optimization, Segmentation, Autoencoder, CIFAR-10Abstract
A fascinating skill in computer vision under Artificial intelligence is the technique of automatically changing monochrome photos into colour ones without human assistance. When a substantial annotated dataset is not readily accessible, transfer learning is commonly employed as the preferred approach. Typically, this involves utilizing pre-trained models with extensive general knowledge gained from training on ImageNet, which are subsequently fine-tuned to cater to specific tasks. From the utility point of view, it is useful in the restoration of movies to the augmentation of photos to increase their readability, re-colorization of pictures, improvement of grayscale drawings, and the restoration of black-and- white photographs. It is believed that automated colorization, in the case of black-and-white movies, has the potential to improve the viewing experiences of viewers. It is possible to utilize it in the sphere of security as well since it can transform the black-and-white photos collected by CCTV cameras into colour ones. In this study, we suggest a method for colouring grayscale images using a Generative Adversarial Network (GAN).
References
Tripathy BK, Anuradha J. Soft computing-advances, and applications. New Delhi: Cengage Learning India Private Limited; 2015.
Maheshwari K, Shaha A, Arya D, Rajasekaran R, Tripathy BK. Convolutional neural networks: a bottom-up approach. Deep Learning Research and Applications. De Gruyter Publications; Boston. 2019; 21–50.
Baktha K, Tripathy BK. Investigation of recurrent neural networks in the field of sentiment analysis. 2017 International Conference on Communication and Signal Processing (ICCSP). 2017; 2047–2050. doi: 10.1109/ICCSP.2017.8286763
Bhandari A, Tripathy B, Adate A, Saxena R, Gadekallu TR. From Beginning to Beginning: Role of Adversarial Learning in Reshaping Generative Models. Electronics. 2023 Jan; 12(1): 155.
Adate A, Tripathy BK. S-LSTM-GAN: Shared Recurrent Neural Networks with Adversarial Training, In: Kulkarni A, Satapathy S, Kang T, Kashan A, editors. Proceedings of the 2nd International Conference on Data Engineering and Communication Technology. Advances in Intelligent Systems and Computing. Vol. 828. Singapore: Springer; 2019; 107–115.
Gui J, Sun Z, Wen Y, Tao D, Ye J. A review on generative adversarial networks: Algorithms, theory, and applications. IEEE Trans Knowl Data Eng. 2021 Nov 23; 35(4): 3313–3332.
Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019; 4401–4410.
Arjovsky M, Chintala S, Bottou L. Wasserstein generative adversarial networks. In International conference on machine learning. 2017 Jul 17; 214–223. PMLR.
Nazeri K, Ng E, Ebrahimi M. Image colorization using generative adversarial net- works. In International conference on articulated motion and deformable objects. 2018 Jul 12; 85–94. Cham: Springer.
Wang X, Guo H, Hu S, Chang MC, Lyu S. Gan-generated faces detection: A survey and new perspectives. arXiv preprint arXiv:2202.07145. 2022 Feb 15.
Gu S, Bao J, Yang H, Chen D, Wen F, Yuan L. Mask-guided portrait editing with conditional gans. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019; 3436–3445.
Zhai X, Cheng Z, Wei Y, Liang Z, Chen Y. Compressive sensing ghost imaging object detection using generative adversarial networks. Opt Eng. 2019 Jan 1; 58(1): 013108.
Courtrai L, Pham MT, Friguet C, Lefèvre S. Small object detection from remote sensing images with the help of object-focused super-resolution using Wasserstein GANs. In IEEE IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium. 2020 Sep 26; 260–263.
Kim SE, Yoon H, Lee J. Fast and scalable earth texture synthesis using spatially assembled generative adversarial neural networks. J Contam Hydrol. 2021 Dec 1; 243: 103867.
Zhao X, Guo J, Wang L, Li F, Zheng J, Yang B. Solid texture synthesis using generative adversarial networks. arXiv preprint arXiv:2102.03973. 2021 Feb 8.
Santurkar S, Ilyas A, Tsipras D, Engstrom L, Tran B, Madry A. Image synthesis with a single (robust) classifier. In: Advances in Neural Information Processing Systems 32. 2019.
Li Y, Li Y, Lu J, Shechtman E, Lee YJ, Singh KK. Collaging class-specific gans for semantic image synthesis. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021; 14418–14427.
Ghiya AS, Vijay V, Ranganath A, Chaturvedi P, Tripathy BK, Sharmila Banu K. Weather Classification: Image Embedding using Convolutional Autoencoder and Predictive Analysis using Stacked Generalization. Presented at the ANTIC conference, BHU. 2021 Dec 17–18.
Gupta R, Sharma A, Kumar A. Super-resolution using gans for medical imaging. Procedia Comput Sci. 2020 Jan 1; 173: 28–35.
Li W, Zhou K, Qi L, Lu L, Lu J. Best-buddy gans for highly detailed image super- resolution. In Proceedings of the AAAI Conference on Artificial Intelligence 2022 Jun 28; 36(2): 1412–1420.
Yi X, Walia E, Babyn P. Generative adversarial network in medical imaging: A review. Med Image Anal. 2019 Dec 1; 58: 101552.
Cai Z, Xiong Z, Xu H, Wang P, Li W, Pan Y. Generative adversarial networks: A survey toward private and secure applications. ACM Comput Surv (CSUR). 2021 Jul 13; 54(6): 1–38.
Bank D, Koenigstein N, Giryes R. Autoencoders. arXiv preprint arXiv:2003.05991. 2020 Mar 12.
Pinaya WH, Vieira S, Garcia-Dias R, Mechelli A. Autoencoders. In Machine learning. 2020 Jan 1; 193–208. Academic Press.
