UCT‐GAN: underwater image colour transfer generative adversarial network. Issue 14 (12th November 2020)

• Record Type: Journal Article
• Authors: Deng, Junjie; Luo, Gege; Zhao, Caidan
• Is Part Of: IET image processing. Volume 14:Issue 14(2020)
• Page Start: 3613
• Page End: 3622
• Publication Date: 2020-11-12
• Subjects: image enhancement -- image colour analysis -- neural nets -- image fusion -- geophysical image processing -- image restoration; image enhancement algorithms -- image quality -- underwater visibility enhancement -- underwater image enhancement neural networks -- underwater image colour transfer generative adversarial network -- UCT‐GAN -- nonlinear mapping function -- image pairs -- inverse function -- multiclass colour transfer network -- colour cast image restoration -- Poisson fusion -- block combination -- training data -- data augmentation method; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.0003
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Underwater image enhancement algorithms improve image quality and indirectly enhance underwater visibility. Although many underwater image enhancement neural networks have been proposed, they require large amounts of data. To reduce the amount of data required while providing better image enhancement, this study proposes an underwater image colour transfer generative adversarial network (UCT‐GAN). The authors first design a non‐linear mapping function to generate colour cast images according to original images. Then, the authors utilise these image pairs (i.e. colour cast images and corresponding original images) to guide the UCT‐GAN in learning the inverse function of the designed non‐linear mapping function. Finally, colour cast images are restored via the inverse function. A data augmentation method based on Poisson fusion and block combination is also proposed to overcome the problem of requiring a large amount of training data. Moreover, the authors extend UCT‐GAN into a multi‐class colour transfer network to achieve an array of underwater image enhancements. Experimental results indicate that the proposed UCT‐GAN can more effectively resolve underwater image colour cast compared to existing algorithms.