期刊文献+

基于预处理图像惩罚的生成对抗网络水下图像增强 被引量:2

Underwater Image Enhancement Based on Generative Adversarial Network with Preprocessed Image Penalty
原文传递
导出
摘要 针对水下图像存在的对比度低、细节模糊、色彩失真问题,提出了一种基于预处理图像惩罚的生成对抗网络(GAN)水下图像增强方法。首先,通过改进的红色通道直方图拉伸算法对水下图像进行预处理,改善图像对比度的同时避免传统直方图拉伸后的局部过增强现象。然后,构建带有预处理图像惩罚的GAN,实现水下图像增强。其中,生成器编码-解码结构中的前两层使用多尺度卷积,以增强网络对细节信息的学习能力。最后,构建多项损失函数,将预处理图像作为伪真值对GAN施加损失惩罚,以提升网络的泛化性能。实验结果表明,相比传统图像增强方法和基于深度学习的图像增强方法,本方法在水下图像的色偏、对比度和细节信息方面的表现更优,且鲁棒性更好。 Aiming at mitigating the problems of low contrast,blurred details,and color distortion in underwater images,an underwater image enhancement method based on preprocessed image penalty and generative adversarial network(GAN)is proposed in this paper.First,an improved red channel histogram stretching algorithm is used to preprocess the input underwater image to improve the image contrast and avoid over enhancement of local blocks after traditional histogram stretching.Then,GAN with preprocessed image penalty is designed to realize underwater image enhancement.Moreover,multiscale convolution is used for the first two layers of the generator coding-decoding structure to enhance the detailed information learning ability of the network.Finally,a multiloss function is established in which the preprocessed image is used as a false truth value to impose loss penalty on GAN to improve generalization performance of the network.Experimental results show that compared with traditional image enhancement methods and deep learning-based image enhancement methods,the method performs better in terms of color deviation,contrast,and detailed information of underwater images,and has better robustness.
作者 宋巍 邢晶晶 杜艳玲 贺琪 Song Wei;Xing Jingjing;Du Yanling;He Qi(Department of Information and Technology,Shanghai Ocean University,Shanghai 201306,China)
出处 《激光与光电子学进展》 CSCD 北大核心 2021年第12期252-263,共12页 Laser & Optoelectronics Progress
基金 国家自然科学基金(61702323,61972240,41906179)。
关键词 图像处理 直方图拉伸 生成对抗网络 惩罚损失 水下图像增强 image processing histogram stretching generative adversarial network penalty loss underwater image enhancement
  • 引文网络
  • 相关文献

参考文献4

二级参考文献11

共引文献44

同被引文献10

引证文献2

二级引证文献2

;
使用帮助 返回顶部