Abstract:
Super resolution (SR) image reconstruction refers to a process of generating a high resolution image from several low resolution images. There is a high demand for high-resolution satellite sensing in modern applications. SR offers an affordable solution for this high demand. The accuracy of super resolution depends on the accuracy of determining the difference between the low-resolution images. The widespread use of super-resolution methods, in a variety of applications such as remote sensing has led to an increasing need for or quality assessment measures. Assessment for image quality traditionally needs its original image as a reference. The traditional method for assessment like Peak Signal to Noise Ratio (PSNR) or Mean Square Error (MSE) difficult when there is no reference. This paper is focused on No-Reference (NR) quality measures for SR images using blur and sharpness (CPBD, LPC-SI). A non-reference objective measure is proposed, which aims to evaluate the quality of the super-resolution satellite images that are constructed without the need for a full reference condition and the result will be reliable. This article presents an overview assessment of SR techniques and measuring the quality of the image. We illustrate shift estimation which is the first and the most critical step in super resolution process. Then several super resolution reconstruction techniques have been discussed and compared. Satellite images (SPOT-5) and other Remote Sensing (RS) data are used in the experiment. The images have sub pixel shifts 0.5 in the horizontal and vertical directions respectively.