利用Contourlet-SSIM视觉模型的IKONOS图像质量评价研究

Image Quality Assessment of IKONOS Images Basedon Contourlet-SIIM Model

  • 摘要: 针对遥感图像质量评价问题,提出了基于Contourlet变换的结构相似性(SSIM)评价的视觉模型。首先,通过25位遥感专业人员对经过处理的200幅高斯模糊图像、200幅椒盐噪声图像、500幅压缩失真图像进行评价,建立主观评分库;然后对经过Contourlet变换后的IKONOS图像进行C-SSIM质量评价;最后将C-SSIM评价结果回归到主观评价空间,与均方误差、峰值信噪比、SSIM评价结果相比,本文方法与主观评价数据库较为一致,并优于其他质量评价模型。

     

    Abstract: To assess the remote sensing image quality,a novel human vision system model is proposedbased on the SSIM of Contourlet transform.Firstly,a subjective image quality assessment database isestablished with 200Gaussian-noise images,200Salt& Pepper noise images,and 500compressiondistortion images,processed in matlab7and then evaluated by 25remote sensing experts.Secondly,IKONOS images after Contourlet transform are assessed by C-SSIM model.Lastly,experiments showthat the C-SSIM model performs better than others,in contrast to MSE,PSNR,SSIM image qualityassessment results,is the contourlet-SIIM Model result are consistent with the subjective database.

     

/

返回文章
返回