基于多尺度对抗网络的水下图像增强方法
Underwater Image Enhancement Based on Multi-scale Adversarial Network
曾俊扬 1司占军2
作者信息
- 1. 天津科技大学 轻工科学与工程学院,天津 300457
- 2. 天津科技大学 轻工科学与工程学院,天津 300457;天津科技大学 人工智能学院,天津 300457
- 折叠
摘要
为了解决水下图像的细节模糊和颜色失真问题,本研究提出了一种基于多尺度对抗网络的水下图像增强方法.首先,通过提出的残差密集块将各层的局部特征增强为全局特征,确保生成的图像保留更多细节.其次,采用多尺度结构提取原始图像的多尺度语义特征.最后,通过自适应融合模块将双通道获得的特征进行融合,进一步优化特征.本研究中判别网络采用马尔可夫判别器结构.此外,通过构建均方误差、结构相似性和感知颜色损失函数,生成的图像在结构、颜色和内容上与参考图像一致.实验结果表明,本研究提出算法的水下图像去模糊增强效果良好,有效改善了水下图像颜色的偏差.在主观和客观评价指标上,所提算法的实验结果均优于对比算法.
Abstract
In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.
关键词
水下图像增强/生成式对抗网络/多尺度特征提取/残差密集块Key words
Underwater image enhancement/Generative adversarial network/Multi-scale feature extraction/Residual dense block引用本文复制引用
出版年
2024
NETL
NSTL
万方数据