摘要
针对遥感图像中常见的噪声污染问题,文章研究基于字典学习和稀疏表示的去噪方法,首先介绍了K-SVD字典学习和正交匹配追踪(OMP)稀疏重建方法。将所提方法应用到加性高斯噪声的退化图像复原中,并用峰值信噪比(PSNR)和结构相似度(SSIM)两个参数进行量化对比,实验结果显示,文章方法在视觉和量化指标上都取得了良好的去噪效果。
Aiming at the common noise pollution problem of remote sensing images,this paper proposed a denoising method based on dictionary learning and sparse representation to solve it.Firstly,the K-SVD dictionary learning and Orthogonal Matching Pursuit(OMP)sparse reconstruction method are introduced.The proposed method in this paper was applied to the restoration of degraded images with additive Gaussian noise and the parameters of peak signal-to-noise ratio(PSNR)and structural similarity(SSIM)are used for quantitative comparison.The experimental results show that the proposed method had achieved good denoising effect in visual and quantitative parameters.
作者
李清运
车守全
王浪威
LI Qing-yun;CHE Shou-quan;WANG Lang-wei(School of mining and mechanical engineering,Liupanshui Normal University,Guizhou 553000)
出处
《山东工业技术》
2022年第4期77-81,共5页
Journal of Shandong Industrial Technology
基金
贵州省大学生创新创业训练计划项目(202110977058)。