Paper
19 October 2022 Image colorization using generative adversarial network
Erxi Cheng, Ruiqian Ma, Ruichen Qi, Yupeng Tang
Author Affiliations +
Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 122943Z (2022) https://doi.org/10.1117/12.2641206
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China
Abstract
In this paper, we present an automatic colorization model for gray scale images based on a generative adversarial networks (GAN). The proposed model is composed of U-Net structure generator and a discriminator with multi-layer convolutional neural network. Then the loss function and weights of true reliability value in the discriminator are optimized. Finally, the corresponding constructed gray scale images colored and colored images are used for training to get an automatic coloring model. In experiments section, we provide various visualization results to validate the effectiveness of our method. The result of a large number of gray scale images coloring experiments show that the model has good learning ability on color transfer and can achieve better coloring effects.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Erxi Cheng, Ruiqian Ma, Ruichen Qi, and Yupeng Tang "Image colorization using generative adversarial network", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 122943Z (19 October 2022); https://doi.org/10.1117/12.2641206
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
RGB color model

Image processing

Gallium nitride

Ultraviolet radiation

Convolutional neural networks

Visual process modeling

Visualization

Back to Top