M.A. Thesis:

images quality metric for blurred images

Image processing today is the best tool for extracting features and analyzing the situation and ultimately making the right decisions. In the case of humans, the same way, information is transmitted through the eye to the brain, and the brain processes and decides the final decision. The purpose of the image processing is to implement the human mind's performance in relation to data and processing. Specifics for extraction of the required attributes to reach a predetermined goal. With the increasing diffusion of discrete information processing methods such as scanners and digital cameras, image processing has been widely used. The resulting images from this information are always more or less associated with some noise and in some cases also have the problem of fading the boundaries of the samples inside the image, which reduces the resolution of the received image. One of the human problems in recent years is which picture has the quality of its work, which image is blurry or noisy and to what extent this is damaging. Even the type of damage has always been questioned so that it solves if possible. If there is an image in the system, the question is, what is the quality of this image? The answer to the image quality evaluation methods is used.

Keywords: : Tar images, PSNR, MSE, SSIM, PSF expansion point function