Coloração de Imagens de Faces Utilizando Autoencoder
Resumo
Até a década de 40 grande parte das fotografias foram produzidas em preto e branco. Trazer um pouco mais de realismo a essas relíquias históricas custa tempo e dinheiro com os métodos não automáticos usados para coloração de fotos. Visando melhorar essas questões, é proposto neste trabalho o uso de uma arquitetura de rede neural conhecida como Autoencoder U-NET para construção de um modelo para colorir imagens. O modelo construído neste trabalho mostra que é possível usar o Autoencoder U-NET para colorir imagens faciais de forma automática.
Palavras-chave:
Coloração de imagens, Autoencoder, celebA
Referências
Cao, Y., Zhou, Z., Zhang, W., and Yu, Y. (2017). Unsupervised Diverse Colorization via Generative Adversarial Networks, pages 151–166. DOI: 10.1007/978-3-319-71249-9_10.
Foster, D. (2019). Generative Deep Learning. O’Reilly Media, Sebastopol, CA, USA.
Gernsheim, H. (1986). A concise history of photography. Number 10. Courier Corporation.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial networks. Advances in Neural Information Processing Systems, 3. DOI: 10.1145/3422622.
InstaRestoration (2020). History of photo colorization. Disponível em: [link]. Acesso em: 07 maio 2022.
Jason Brownlee (2020). Autoencoder feature extraction for classification. Disponível em: [link]. Acesso em: 07 maio 2022.
Karras, T., Laine, S., and Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4396–4405. DOI: 10.1109/CVPR.2019.00453.
Liu, Z., Luo, P., Wang, X., and Tang, X. (2015). Deep learning face attributes in the wild. In Proceedings of International Conference on Computer Vision (ICCV). DOI: 10.1109/ICCV.2015.425.
Persch, J., Pierre, F., and Steidl, G. (2017). Exemplar-based face colorization using image morphing. Journal of Imaging, 3(4). DOI: 10.3390/jimaging3040048.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pages 234–241, Cham. DOI: 10.1007/978-3-319-245744, 28.
Treneska, S., Zdravevski, E., Pires, I. M., Lameski, P., and Gievska, S. (2022). Ganbasedimage colorization for self-supervised visual feature learning. Sensors, 22(4). DOI: 10.3390/s22041599.
Yi, D., Lei, Z., Liao, S., and Li, S. Z. (2014). Learning face representation from scratch. arXiv preprint arXiv:1411.7923. DOI: 10.48550/arXiv.1411.7923.
Zaware, S., Pathak, D., Patil, V., Sangale, G., and Gupta, V. (2021). Gray scale image colorization for human faces. In 2021 International Conference on Design Innovations for 3Cs Compute Communicate Control (ICDI3C), pages 107–110. DOI: 10.1109/ICDI3C53598.2021.00030.
Foster, D. (2019). Generative Deep Learning. O’Reilly Media, Sebastopol, CA, USA.
Gernsheim, H. (1986). A concise history of photography. Number 10. Courier Corporation.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial networks. Advances in Neural Information Processing Systems, 3. DOI: 10.1145/3422622.
InstaRestoration (2020). History of photo colorization. Disponível em: [link]. Acesso em: 07 maio 2022.
Jason Brownlee (2020). Autoencoder feature extraction for classification. Disponível em: [link]. Acesso em: 07 maio 2022.
Karras, T., Laine, S., and Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4396–4405. DOI: 10.1109/CVPR.2019.00453.
Liu, Z., Luo, P., Wang, X., and Tang, X. (2015). Deep learning face attributes in the wild. In Proceedings of International Conference on Computer Vision (ICCV). DOI: 10.1109/ICCV.2015.425.
Persch, J., Pierre, F., and Steidl, G. (2017). Exemplar-based face colorization using image morphing. Journal of Imaging, 3(4). DOI: 10.3390/jimaging3040048.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pages 234–241, Cham. DOI: 10.1007/978-3-319-245744, 28.
Treneska, S., Zdravevski, E., Pires, I. M., Lameski, P., and Gievska, S. (2022). Ganbasedimage colorization for self-supervised visual feature learning. Sensors, 22(4). DOI: 10.3390/s22041599.
Yi, D., Lei, Z., Liao, S., and Li, S. Z. (2014). Learning face representation from scratch. arXiv preprint arXiv:1411.7923. DOI: 10.48550/arXiv.1411.7923.
Zaware, S., Pathak, D., Patil, V., Sangale, G., and Gupta, V. (2021). Gray scale image colorization for human faces. In 2021 International Conference on Design Innovations for 3Cs Compute Communicate Control (ICDI3C), pages 107–110. DOI: 10.1109/ICDI3C53598.2021.00030.
Publicado
28/11/2023
Como Citar
SANTOS, Mateus Reis; TEIXEIRA, Raoni Florentino da Silva; MARINS, Joyce Aline; GUARIENTI, Gracyeli Santos Souza; CERUTTI, Alisson; SOUZA, Joao Vitor Monteiro.
Coloração de Imagens de Faces Utilizando Autoencoder. In: ESCOLA REGIONAL DE INFORMÁTICA DE MATO GROSSO (ERI-MT), 12. , 2023, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 21-30.
ISSN 2447-5386.
DOI: https://doi.org/10.5753/eri-mt.2023.236050.
