No-reference remote sensing image quality assessment using a comprehensive evaluation factor
Lin Wang, Xu Wang, Xiaoli Li, Xiaopeng Shao · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2014
The conventional image quality assessment algorithm, such as Peak Signal to Noise Ratio （PSNR）， Mean Square Error（MSE） and structural similarity (SSIM), needs the original image as a reference. It’s not applicable to the remote sensing image for which the original image cannot be assumed to be available. In this paper, a No-reference Image Quality Assessment (NRIQA) algorithm is presented to evaluate the quality of remote sensing image. Since blur and noise (including the stripe noise) are the common distortion factors affecting remote sensing image quality, a comprehensive evaluation factor is modeled to assess the blur and noise by analyzing the image visual properties for different incentives combined with SSIM based on human visual system (HVS), and also to assess the stripe noise by using Phase Congruency (PC). The experiment results show this algorithm is an accurate and reliable method for Remote Sensing Image Quality Assessment.